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

    Neuronpedia

    INDEX
    Explanations

    master

    np_max-act · gemini-2.0-flash

    The neuron responds to mentions of “teacher” and “student” models (and related distillation terms) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    盤
    -0.07
    groups
    -0.06
    ché
    -0.06
    ⠀
    -0.06
    pe
    -0.06
    *****
    -0.06
     Riyadh
    -0.06
    	graph
    -0.06
    ('/')
    -0.06
    resize
    -0.06
    POSITIVE LOGITS
     oblivious
    0.07
    .Messaging
    0.07
     Vit
    0.06
     Lip
    0.06
     mell
    0.06
     resolutions
    0.06
    ecess
    0.06
    <QString
    0.06
    	Default
    0.06
    uits
    0.06
    Act Density 0.036%

    No Known Activations