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

    Neuronpedia

    INDEX
    Explanations

    Phone numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hog
    -0.07
     march
    -0.07
     trường
    -0.07
    ⽥
    -0.06
    taken
    -0.06
    WINDOW
    -0.06
    	exit
    -0.06
    actual
    -0.06
    =batch
    -0.06
    ܕ
    -0.06
    POSITIVE LOGITS
    _COST
    0.07
     Emma
    0.07
     Closed
    0.07
    _unique
    0.07
    EntityType
    0.07
    essim
    0.07
    羕
    0.07
    WebResponse
    0.07
    ToLeft
    0.07
     Hurt
    0.07
    Act Density 0.002%

    No Known Activations