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

    Neuronpedia

    INDEX
    Explanations

    .h

    np_max-act · gemini-2.0-flash

    This neuron detects C preprocessor include directives (especially “#include <linux/module.h>”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    $core
    -0.07
    _OBJ
    -0.07
    ())))
    -0.07
     b
    -0.06
    :])↵
    -0.06
    Coefficient
    -0.06
    .loading
    -0.06
    .Types
    -0.06
    紧
    -0.06
     bmi
    -0.06
    POSITIVE LOGITS
     muscular
    0.06
    rella
    0.06
     gösteren
    0.06
    PRO
    0.06
    Multiply
    0.06
     inquiries
    0.06
     Copyright
    0.06
    주
    0.06
     جدا
    0.06
    amacare
    0.06
    Act Density 0.000%

    No Known Activations