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

    Neuronpedia

    INDEX
    Explanations

    fit in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    atter
    -0.07
     pipes
    -0.06
    gr
    -0.06
     multiplic
    -0.06
    -word
    -0.06
    rist
    -0.06
     intentions
    -0.06
    參
    -0.06
    город
    -0.06
     Chop
    -0.06
    POSITIVE LOGITS
     []*
    0.07
    =$_
    0.07
    INIT
    0.06
    ========
    0.06
    /std
    0.06
    SESSION
    0.06
     massacre
    0.06
    では
    0.06
    .include
    0.06
    /{}/
    0.06
    Act Density 0.034%

    No Known Activations