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

    Neuronpedia

    INDEX
    Explanations

    hands

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ekkür
    -0.07
     paving
    -0.07
     nexus
    -0.06
    .SerializeObject
    -0.06
    าประ
    -0.06
    ادة
    -0.06
     Lobby
    -0.06
    -Cola
    -0.06
    (ro
    -0.06
    건
    -0.06
    POSITIVE LOGITS
     toxicity
    0.07
     Efficient
    0.07
     Dominican
    0.06
    iselect
    0.06
     است
    0.06
    limit
    0.06
    母
    0.06
     составе
    0.06
    (","
    0.06
     supervision
    0.06
    Act Density 0.004%

    No Known Activations