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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of academic institutions or affiliations, especially university names.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     эта
    -0.07
    MBED
    -0.07
     kube
    -0.07
    Geom
    -0.06
    트
    -0.06
     Glob
    -0.06
    �
    -0.06
    /**<
    -0.06
     acest
    -0.06
     saline
    -0.06
    POSITIVE LOGITS
     осві
    0.07
    cedes
    0.06
    增
    0.06
    lexer
    0.06
     gridBagConstraints
    0.06
    ποί
    0.06
    onec
    0.06
    .prepend
    0.06
     พระ
    0.06
    canvas
    0.06
    Act Density 0.009%

    No Known Activations