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

    Neuronpedia

    INDEX
    Explanations

    android

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric literals—especially floating‐point numbers—in Android XML attribute values.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .filtered
    -0.08
    _LEAVE
    -0.07
     landmarks
    -0.06
     дані
    -0.06
     Vale
    -0.06
    attributes
    -0.06
    MA
    -0.06
    Ever
    -0.06
     AttributeSet
    -0.06
     месте
    -0.06
    POSITIVE LOGITS
     ağ
    0.07
    Arguments
    0.06
    ...",↵
    0.06
     广
    0.06
    ेब
    0.06
    cerpt
    0.06
    ored
    0.06
    riangle
    0.06
    continental
    0.06
    TabControl
    0.06
    Act Density 0.005%

    No Known Activations