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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     SMB
    -0.07
    _UNDEFINED
    -0.07
    (turn
    -0.06
     خم
    -0.06
    flare
    -0.06
     Murdoch
    -0.06
     Vad
    -0.06
    人
    -0.06
    -0.06
    жд
    -0.06
    POSITIVE LOGITS
    (QtCore
    0.07
    AllowAnonymous
    0.07
     unilateral
    0.06
     editText
    0.06
     negotiations
    0.06
    .hasNext
    0.06
     sweetness
    0.06
     intox
    0.06
     تش
    0.06
    .transactions
    0.06
    Act Density 0.098%

    No Known Activations