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
    codegen
    -0.07
    bish
    -0.07
     replicated
    -0.06
     wealthy
    -0.06
    Strict
    -0.06
     Predicate
    -0.06
    壓
    -0.06
     scale
    -0.06
    ugu
    -0.06
     कन
    -0.06
    POSITIVE LOGITS
     پشت
    0.06
    (Page
    0.06
    资格
    0.06
     maxLength
    0.06
    صف
    0.06
     mỹ
    0.06
    (point
    0.06
    �
    0.06
    (report
    0.06
    afs
    0.06
    Act Density 0.000%

    No Known Activations