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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     visual
    -0.07
    _life
    -0.06
     oppressive
    -0.06
    >Total
    -0.06
     level
    -0.06
     surgical
    -0.06
    ł
    -0.06
     astronomers
    -0.06
     spectrum
    -0.06
     ICollection
    -0.06
    POSITIVE LOGITS
     ");
↵
    0.08
    fois
    0.07
     olmuştur
    0.06
     состоянии
    0.06
    ").↵
    0.06
     tenga
    0.06
     увид
    0.06
     SUBSTITUTE
    0.06
    Ay
    0.06
     Shorts
    0.06
    Act Density 0.028%

    No Known Activations