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

    Neuronpedia

    INDEX
    Explanations

    Customer reviews/Q&A

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     побач
    -0.08
    (Status
    -0.08
    .company
    -0.07
    WithData
    -0.06
     éxito
    -0.06
    Gray
    -0.06
    /***/
    -0.06
    нож
    -0.06
    InstantiationException
    -0.06
     subclass
    -0.06
    POSITIVE LOGITS
     uniquely
    0.07
    omid
    0.07
    oi
    0.06
    _dense
    0.06
     ll
    0.06
     obsolete
    0.06
    _reads
    0.06
     butterflies
    0.06
     pre
    0.06
     인터넷
    0.06
    Act Density 0.046%

    No Known Activations