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
    endra
    -0.07
    Taken
    -0.07
    خذ
    -0.07
     Self
    -0.06
    .Free
    -0.06
    LICENSE
    -0.06
     Dj
    -0.06
    튄
    -0.06
    _STORE
    -0.06
    矧
    -0.06
    POSITIVE LOGITS
     материалы
    0.08
    Connections
    0.07
     mim
    0.07
    失望
    0.07
    (results
    0.07
     followers
    0.07
    价值观
    0.07
     كبير
    0.07
     manpower
    0.07
    בהיר
    0.07
    Act Density 0.001%

    No Known Activations