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

    Neuronpedia

    INDEX
    Explanations

    say ".String"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ς
    -0.07
    AGER
    -0.07
    Split
    -0.07
    .
↵
↵
    -0.07
    ��
    -0.06
    ίες
    -0.06
     trò
    -0.06
    —
    -0.06
    revolution
    -0.06
    	Value
    -0.06
    POSITIVE LOGITS
    material
    0.06
     ofrec
    0.06
    加工
    0.06
     cancers
    0.06
     Feeling
    0.06
     치
    0.06
     답
    0.06
     //================================================================
    0.06
     Andrea
    0.06
    .guard
    0.06
    Act Density 0.002%

    No Known Activations