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

    Neuronpedia

    INDEX
    Explanations

    model

    np_max-act · gemini-2.0-flash

    This neuron detects technical terms referring to molecular or structural modeling and related methodological descriptions in scientific text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     molec
    -0.07
     Struct
    -0.07
     mec
    -0.06
    mín
    -0.06
    -0.06
    handle
    -0.06
    ponde
    -0.06
    _estimator
    -0.06
     perseverance
    -0.06
    busters
    -0.06
    POSITIVE LOGITS
     участь
    0.06
    "][$
    0.06
     aided
    0.06
    ]+
    0.06
    ű
    0.06
     роль
    0.06
    WiFi
    0.06
     Arduino
    0.06
     blockDim
    0.06
    」を
    0.06
    Act Density 0.031%

    No Known Activations