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

    Neuronpedia

    INDEX
    Explanations

    endorse

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ars
    -0.07
     parliamentary
    -0.06
     Mold
    -0.06
     maps
    -0.06
     Pure
    -0.06
     grenades
    -0.06
     Nature
    -0.06
    ilde
    -0.06
    Complete
    -0.06
    рид
    -0.06
    POSITIVE LOGITS
    _BUCKET
    0.08
    _NR
    0.07
    //
↵
    0.06
    ULONG
    0.06
    koli
    0.06
    terraform
    0.06
    /black
    0.06
     sắt
    0.06
    ££
    0.06
    .getTag
    0.06
    Act Density 0.010%

    No Known Activations