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

    Neuronpedia

    INDEX
    Explanations

    math equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sprintf
    -0.08
     consultant
    -0.07
    /string
    -0.07
     problems
    -0.06
    _REASON
    -0.06
    _sf
    -0.06
     نامه
    -0.06
     Marilyn
    -0.06
     algumas
    -0.06
     verification
    -0.06
    POSITIVE LOGITS
    شن
    0.06
    ollo
    0.06
     tossed
    0.06
    "}↵
    0.06
     Whats
    0.06
    ุมภาพ
    0.06
     [+
    0.06
     сказала
    0.06
     jaký
    0.06
    kil
    0.06
    Act Density 0.004%

    No Known Activations