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

    Neuronpedia

    INDEX
    Explanations

    is has are

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (`${
    -0.07
     поверхности
    -0.07
    uzzy
    -0.07
     �
    -0.06
    655
    -0.06
    ся
    -0.06
    残
    -0.06
    лых
    -0.06
     Integration
    -0.06
     Rico
    -0.06
    POSITIVE LOGITS
     prayers
    0.07
    ?“
    0.07
    yb
    0.07
     παρ
    0.06
     abduction
    0.06
    Mel
    0.06
    .jav
    0.06
    eur
    0.06
     Αλ
    0.06
     polit
    0.06
    Act Density 0.071%

    No Known Activations