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

    Neuronpedia

    INDEX
    Explanations

    linearity

    np_max-act · gemini-2.0-flash

    This neuron responds to technical performance‐specification terms (e.g. “linearity,” “stability,” “response,” “control”) describing sensor or device characteristics.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _stat
    -0.07
    乐
    -0.07
     run
    -0.07
     Jal
    -0.07
     Burr
    -0.07
     evil
    -0.07
    ця
    -0.07
    lescope
    -0.06
     amp
    -0.06
     Narrative
    -0.06
    POSITIVE LOGITS
     investments
    0.06
    ัดการ
    0.06
    lası
    0.06
    .But
    0.06
     renting
    0.06
    PI
    0.06
    	labels
    0.06
    ัญช
    0.06
    )$_
    0.06
     ListView
    0.06
    Act Density 0.014%

    No Known Activations