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

    Neuronpedia

    INDEX
    Explanations

    SQLiteDatabase

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     notorious
    -0.07
     С
    -0.07
     М
    -0.07
    からの
    -0.07
     jackpot
    -0.07
    =<?=
    -0.07
    名称
    -0.06
     W
    -0.06
     Vor
    -0.06
     trotz
    -0.06
    POSITIVE LOGITS
     �
    0.06
    .Usage
    0.06
     Baghdad
    0.06
    uesta
    0.06
    though
    0.06
    .ModelAdmin
    0.06
    âng
    0.06
    敏
    0.06
    atted
    0.06
     applicationWill
    0.05
    Act Density 0.001%

    No Known Activations