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

    Neuronpedia

    INDEX
    Explanations

    parentheses

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /font
    -0.07
    ossier
    -0.07
    logical
    -0.07
    Ids
    -0.07
    %,
    -0.07
     Hector
    -0.07
     OnTriggerEnter
    -0.06
    ortic
    -0.06
     attachments
    -0.06
     checkpoints
    -0.06
    POSITIVE LOGITS
    멱
    0.07
    屦
    0.07
    мот
    0.07
    澭
    0.07
    姱
    0.07
    ประกอบ
    0.07
     Nachricht
    0.07
     uwag
    0.06
    恁
    0.06
     oppression
    0.06
    Act Density 0.026%

    No Known Activations