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

    Neuronpedia

    INDEX
    Explanations

    terms describing uncertainty or ambiguity

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

    qualifying appearance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SharedDtor
    -0.50
    ftagPool
    -0.49
    withIdentifier
    -0.48
    PMailer
    -0.48
     hoogte
    -0.43
    MessageOf
    -0.42
    bkz
    -0.38
    principalTable
    -0.38
    этому
    -0.37
    蒻
    -0.37
    POSITIVE LOGITS
     seemingly
    0.71
     seeming
    0.59
     apparent
    0.55
    一見
    0.54
    ViewInit
    0.53
    seem
    0.52
    Appear
    0.51
     apparente
    0.50
    apparent
    0.49
     Seem
    0.48
    Act Density 0.030%

    No Known Activations