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

    Neuronpedia

    INDEX
    Explanations

    forum discussions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     IS
    -0.07
     costing
    -0.07
     Dou
    -0.06
    ाज
    -0.06
     Duc
    -0.06
     Modifications
    -0.06
    Dog
    -0.06
     posted
    -0.06
     discharge
    -0.06
     loops
    -0.06
    POSITIVE LOGITS
    HandlerContext
    0.07
     faction
    0.07
     sessions
    0.07
    .Down
    0.06
    ıyorlar
    0.06
    .predicate
    0.06
    ;q
    0.06
     fills
    0.06
    /reg
    0.06
     فيه
    0.06
    Act Density 0.014%

    No Known Activations