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

    Neuronpedia

    INDEX
    Explanations

    references to emotional expressions and personal statements

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

    English fiction and personal memoirs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ujednoznacz
    -0.81
     '\\;'
    -0.64
    tagHelperRunner
    -0.63
    rungsseite
    -0.59
    ttemberg
    -0.58
     transfieras
    -0.58
     ſta
    -0.57
     podjela
    -0.57
     للمعارف
    -0.57
     dependencia
    -0.55
    POSITIVE LOGITS
    esModule
    0.37
     Spez
    0.36
    trace
    0.34
     anonim
    0.33
    mem
    0.32
    lbl
    0.32
    Id
    0.31
    label
    0.31
    MC
    0.31
    ècie
    0.30
    Act Density 0.080%

    No Known Activations