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

    Neuronpedia

    INDEX
    Explanations

    Character names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .tooltip
    -0.08
    ,Q
    -0.07
     tank
    -0.07
    (Window
    -0.07
    .offer
    -0.07
     encouragement
    -0.07
     Looks
    -0.07
     inbound
    -0.07
    =q
    -0.06
     приг
    -0.06
    POSITIVE LOGITS
     CALC
    0.06
    .exchange
    0.06
     psychedelic
    0.06
     nation
    0.06
    .Errorf
    0.06
    romosome
    0.06
     Netanyahu
    0.06
    证券
    0.06
     landsc
    0.06
    eded
    0.05
    Act Density 0.025%

    No Known Activations