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

    Neuronpedia

    INDEX
    Explanations

    <

    np_max-act · gemini-2.0-flash

    The neuron fires on the ‘<’ character that begins an angle‐bracketed C++ header or template name.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     predic
    -0.07
    otyp
    -0.07
     ід
    -0.06
    _dataset
    -0.06
    save
    -0.06
    '>"+
    -0.06
     expr
    -0.06
    }s
    -0.06
    ิตร
    -0.06
    .Created
    -0.06
    POSITIVE LOGITS
    required
    0.07
     немного
    0.06
    	lbl
    0.06
    paněl
    0.06
    ottom
    0.06
     Gef
    0.06
    ategorie
    0.06
    TouchUpInside
    0.06
     نشان
    0.06
     Swansea
    0.06
    Act Density 0.001%

    No Known Activations