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

    Neuronpedia

    INDEX
    Explanations

    code comments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    我的
    -0.07
     пох
    -0.06
    /script
    -0.06
     Sey
    -0.06
     insult
    -0.06
     Jump
    -0.06
    (Constructor
    -0.06
     Specific
    -0.06
    March
    -0.06
     بخش
    -0.06
    POSITIVE LOGITS
     urb
    0.06
    Russ
    0.06
    заб
    0.06
    .vec
    0.06
    _NB
    0.06
     gb
    0.06
    DDR
    0.06
    _ring
    0.06
    gb
    0.05
     tvar
    0.05
    Act Density 0.023%

    No Known Activations