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

    Neuronpedia

    INDEX
    Explanations

    this/self

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (win
    -0.07
    enate
    -0.07
    /he
    -0.07
    >b
    -0.06
     funny
    -0.06
     guy
    -0.06
    Disney
    -0.06
     да
    -0.06
    slave
    -0.06
     ノ
    -0.06
    POSITIVE LOGITS
    訴
    0.07
    -li
    0.06
     drunken
    0.06
    dcc
    0.06
    .TRAILING
    0.06
     Köy
    0.06
    综合
    0.06
    reement
    0.06
     Measurement
    0.06
    AGES
    0.06
    Act Density 0.005%

    No Known Activations