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

    Neuronpedia

    INDEX
    Explanations

    behavioral

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     punishing
    -0.06
    فران
    -0.06
     宮
    -0.06
     tys
    -0.06
     Failed
    -0.06
    (cpu
    -0.06
    анні
    -0.06
     frogs
    -0.06
    .metrics
    -0.06
    course
    -0.06
    POSITIVE LOGITS
    -нибудь
    0.07
    uards
    0.06
    idental
    0.06
    cox
    0.06
     fists
    0.06
     hitter
    0.06
     Bark
    0.06
     ممن
    0.06
    ेदन
    0.06
     direct
    0.06
    Act Density 0.008%

    No Known Activations