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

    Neuronpedia

    INDEX
    Explanations

    delta

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ricky
    -0.06
    uru
    -0.06
    lernen
    -0.06
     Spr
    -0.06
    (un
    -0.06
    orado
    -0.06
     Bentley
    -0.06
    subseteq
    -0.06
     jeopardy
    -0.06
    CompleteListener
    -0.06
    POSITIVE LOGITS
    عل
    0.07
    "h
    0.06
    ensely
    0.06
     polož
    0.06
     вос
    0.06
     darm
    0.06
     flash
    0.06
    @Module
    0.06
     """↵↵
    0.06
    クト
    0.06
    Act Density 0.003%

    No Known Activations