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

    Neuronpedia

    INDEX
    Explanations

    input

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _calibration
    -0.07
    _visibility
    -0.07
     UIAlertController
    -0.07
    Descri
    -0.06
    .trailingAnchor
    -0.06
    ジョ
    -0.06
    .hstack
    -0.06
     situace
    -0.06
    Classifier
    -0.06
    ственной
    -0.06
    POSITIVE LOGITS
     input
    0.11
    >@
    0.08
     inputs
    0.08
     Input
    0.08
     CONTENT
    0.07
    PP
    0.07
    音
    0.07
     MATERIAL
    0.07
     reference
    0.07
     pointers
    0.07
    Act Density 0.009%

    No Known Activations