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
     CFR
    -0.08
     Therefore
    -0.06
    Invariant
    -0.06
    zx
    -0.06
    enerate
    -0.06
    Therefore
    -0.06
    596
    -0.06
    crime
    -0.06
    货
    -0.06
     However
    -0.06
    POSITIVE LOGITS
     ez
    0.07
     Ek
    0.06
    �
    0.06
     الرمزية
    0.06
    NK
    0.06
     csvfile
    0.06
    rists
    0.06
    ready
    0.06
     EK
    0.06
    whelming
    0.06
    Act Density 0.002%

    No Known Activations