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

    Neuronpedia

    INDEX
    Explanations

    instructions and disclaimers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ZIP
    -0.07
    撕
    -0.07
    _FUNC
    -0.07
    DAC
    -0.07
     jitter
    -0.07
    显示出
    -0.07
     orc
    -0.07
    orch
    -0.07
     الذي
    -0.07
    uddle
    -0.07
    POSITIVE LOGITS
    '(
    0.07
     '::
    0.06
     célib
    0.06
    (Context
    0.06
    istema
    0.06
    ∣
    0.06
    _$_
    0.06
     category
    0.06
     ",",
    0.06
     ellas
    0.06
    Act Density 0.005%

    No Known Activations