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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     σου
    -0.07
     Slut
    -0.06
    ENDED
    -0.06
    credential
    -0.06
     elif
    -0.06
     суще
    -0.06
     friday
    -0.06
    _ANY
    -0.06
    ogeneous
    -0.06
     elseif
    -0.06
    POSITIVE LOGITS
    tesy
    0.07
    _music
    0.06
     Placement
    0.06
    kan
    0.06
    、どう
    0.06
    령
    0.06
     Barney
    0.06
    _patches
    0.06
     Carlson
    0.06
    jets
    0.06
    Act Density 0.023%

    No Known Activations