Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    terms related to being overlooked or undervalued

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    something is underappreciated

    np_acts-logits-general · gemini-2.0-flash

    overlooked, underrated, neglected

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ThroughAttribute
    -0.35
    flashdata
    -0.33
     kır
    -0.31
    PrototypeOf
    -0.31
    '])->
    -0.31
    retum
    -0.31
     keç
    -0.30
     falschen
    -0.29
     Roskov
    -0.29
     masing
    -0.28
    POSITIVE LOGITS
     underrated
    0.79
     overlooked
    0.71
     untapped
    0.66
    Forgotten
    0.66
     unnoticed
    0.64
    glected
    0.63
     neglected
    0.63
     unexplored
    0.63
     forgotten
    0.61
    errated
    0.61
    Act Density 0.514%

    No Known Activations