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

    Neuronpedia

    INDEX
    Explanations

    question marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     yaşam
    -0.08
     Pane
    -0.08
    redicate
    -0.07
    .pen
    -0.07
     Jong
    -0.06
     Seventh
    -0.06
    zza
    -0.06
    Goal
    -0.06
     Tournament
    -0.06
    ολ
    -0.06
    POSITIVE LOGITS
    เคราะห
    0.07
     bitcoins
    0.06
    _Zero
    0.06
    PERSON
    0.06
    }*/↵↵
    0.06
     رض
    0.06
     segundos
    0.06
     Gly
    0.06
     enlightened
    0.06
    has
    0.06
    Act Density 0.004%

    No Known Activations