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

    Neuronpedia

    INDEX
    Explanations

    endpoints

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     whilst
    -0.08
    /module
    -0.07
    akit
    -0.07
     rising
    -0.07
     moat
    -0.07
     assinatura
    -0.07
    موال
    -0.07
    andbox
    -0.07
     affirmative
    -0.07
     مجلة
    -0.07
    POSITIVE LOGITS
     конц
    0.11
    ड़े
    0.08
     этап
    0.08
     legs
    0.08
     окончания
    0.08
     кор
    0.08
    smöglichkeiten
    0.08
     pairs
    0.08
     располож
    0.08
     각각
    0.08
    Act Density 0.009%

    No Known Activations