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

    Neuronpedia

    INDEX
    Explanations

    Punctuation/repeated characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     inevitable
    -0.07
    rieving
    -0.07
     Cancel
    -0.07
    -REAL
    -0.07
     Evil
    -0.07
    3
    -0.07
    Album
    -0.07
     Dice
    -0.06
     patron
    -0.06
     Honor
    -0.06
    POSITIVE LOGITS
    (-
    0.07
     interacting
    0.06
     Xiao
    0.06
    esti
    0.06
     construct
    0.06
    ????
    0.06
    Elect
    0.06
    versed
    0.06
    ologically
    0.06
    ği
    0.06
    Act Density 0.018%

    No Known Activations