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

    Neuronpedia

    INDEX
    Explanations

    code and programming errors

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     depends
    -0.06
     preach
    -0.06
     plot
    -0.06
     이름
    -0.06
    ाहन
    -0.06
     strncmp
    -0.06
     визнача
    -0.06
     chain
    -0.06
    <Address
    -0.06
     unless
    -0.06
    POSITIVE LOGITS
     ارشد
    0.07
    _AMOUNT
    0.07
    /admin
    0.06
     militants
    0.06
    -y
    0.06
    #[
    0.06
    .Work
    0.06
    žený
    0.06
    scribed
    0.06
    /{{
    0.06
    Act Density 0.175%

    No Known Activations