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

    Neuronpedia

    INDEX
    Explanations

    record

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sister
    -0.07
    ₤
    -0.07
    全力以赴
    -0.07
    isting
    -0.07
     Pam
    -0.06
     suite
    -0.06
    웍
    -0.06
    佥
    -0.06
    iel
    -0.06
    ueling
    -0.06
    POSITIVE LOGITS
    رك
    0.08
     ceremonial
    0.07
    _VECTOR
    0.07
     destroyer
    0.07
    谈论
    0.07
     pharm
    0.07
    avatars
    0.07
     sad
    0.07
     acknowledge
    0.07
     przykład
    0.07
    Act Density 0.002%

    No Known Activations