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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ="">
    -0.08
    �
    -0.08
     Wand
    -0.07
     proof
    -0.07
    LOT
    -0.07
     Ernst
    -0.07
     nonsense
    -0.07
    poon
    -0.06
     MAT
    -0.06
    리스
    -0.06
    POSITIVE LOGITS
    .rm
    0.06
    ط
    0.06
    /token
    0.06
    addir
    0.06
    (seq
    0.06
    warehouse
    0.06
    "]);↵↵
    0.06
    -[
    0.06
     contrario
    0.06
    _cleanup
    0.06
    Act Density 0.000%

    No Known Activations