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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    {*
    -0.07
    /front
    -0.06
    ffe
    -0.06
     stk
    -0.06
    isoft
    -0.06
    _curve
    -0.06
    letics
    -0.06
     Dx
    -0.06
     intends
    -0.06
    sov
    -0.06
    POSITIVE LOGITS
    일본
    0.07
    alah
    0.06
     stronger
    0.06
     hairs
    0.06
    不
    0.06
    _exe
    0.06
    ?</
    0.06
    inst
    0.06
    уск
    0.06
    tik
    0.06
    Act Density 0.079%

    No Known Activations