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

    Neuronpedia

    INDEX
    Explanations

    Scoring points

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    展现了
    -0.08
     obscured
    -0.08
    eks
    -0.07
    trzymać
    -0.07
     goat
    -0.07
    pered
    -0.07
    הייתי
    -0.07
     "***
    -0.07
    倒霉
    -0.07
     Brenda
    -0.07
    POSITIVE LOGITS
    杞
    0.07
    넗
    0.06
    万里
    0.06
    �
    0.06
    DCALL
    0.06
     كلم
    0.06
    ispers
    0.06
     unve
    0.06
    שיח
    0.06
     XF
    0.06
    Act Density 0.001%

    No Known Activations