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

    Neuronpedia

    INDEX
    Explanations

    scientific papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Time
    -0.07
    (clock
    -0.07
    _voltage
    -0.06
    (Location
    -0.06
     Tomb
    -0.06
    _patterns
    -0.06
    _allocator
    -0.06
     tactic
    -0.06
     Doyle
    -0.06
    Intensity
    -0.06
    POSITIVE LOGITS
    eselect
    0.07
    handleSubmit
    0.06
     setSearch
    0.06
     ingen
    0.06
    eview
    0.06
    TokenType
    0.06
    bine
    0.06
    χν
    0.06
    弟
    0.06
    .writeValue
    0.06
    Act Density 0.094%

    No Known Activations