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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    олуч
    -0.07
     Hak
    -0.07
     survival
    -0.07
     penalty
    -0.06
    еж
    -0.06
     až
    -0.06
     kindness
    -0.06
     cultivating
    -0.06
    �
    -0.06
    eten
    -0.06
    POSITIVE LOGITS
    ões
    0.06
    cob
    0.06
    unicip
    0.06
    .slf
    0.06
     monoc
    0.06
    _WEAPON
    0.06
     영화
    0.06
    \Collections
    0.06
    AYS
    0.05
    ♀♀
    0.05
    Act Density 0.092%

    No Known Activations