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

    Neuronpedia

    INDEX
    Explanations

    /

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    PBS
    -0.07
    俎
    -0.06
    ober
    -0.06
     предоставлен
    -0.06
    혓
    -0.06
    inyin
    -0.06
    uez
    -0.06
    ﯢ
    -0.06
    CJK
    -0.06
    仆
    -0.06
    POSITIVE LOGITS
     Rangers
    0.08
     onUpdate
    0.08
    女
    0.07
     Stars
    0.07
     Round
    0.07
    ᠮ
    0.07
    ouched
    0.07
    erdings
    0.07
     rewrite
    0.07
    -road
    0.07
    Act Density 0.001%

    No Known Activations