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

    Neuronpedia

    INDEX
    Explanations

    adds

    np_max-act · gemini-2.0-flash

    The neuron is keyed to reporting verbs and speaker attributions (e.g. “said,” “adds,” “explained,” “stated”) that signal quoted speech.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    اعات
    -0.07
     вияв
    -0.07
    PerPixel
    -0.06
    ấp
    -0.06
     sen
    -0.06
    ával
    -0.06
     Gu
    -0.06
     Een
    -0.06
    deny
    -0.06
    tour
    -0.06
    POSITIVE LOGITS
    _style
    0.08
    Angle
    0.07
    Check
    0.07
     तन
    0.07
    index
    0.06
    TCHA
    0.06
    irror
    0.06
     Chaos
    0.06
    .radioButton
    0.06
     Medina
    0.06
    Act Density 0.032%

    No Known Activations