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

    Neuronpedia

    INDEX
    Explanations

    calculus theorems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Якщо
    -0.08
    огод
    -0.08
    -0.08
     godina
    -0.07
    权益
    -0.07
    umph
    -0.07
    oney
    -0.07
    _pause
    -0.07
     Це
    -0.07
    pọ
    -0.07
    POSITIVE LOGITS
     Lamborghini
    0.08
     Ferrari
    0.08
     macho
    0.08
    参
    0.08
     stoi
    0.07
     lazy
    0.07
     poets
    0.07
     hurd
    0.07
     volg
    0.07
    .lazy
    0.07
    Act Density 0.001%
    No Known Activations