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

    Neuronpedia

    INDEX
    Explanations

    blast

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (dr
    -0.07
    _EDGE
    -0.07
     regularization
    -0.07
    theros
    -0.06
     Care
    -0.06
     nodo
    -0.06
    ##_
    -0.06
     remedies
    -0.06
     Mer
    -0.06
    周
    -0.06
    POSITIVE LOGITS
     labs
    0.07
    orb
    0.07
    ора
    0.07
    toast
    0.07
    east
    0.06
     naw
    0.06
    raised
    0.06
    Ast
    0.06
     بور
    0.06
    азв
    0.06
    Act Density 0.002%

    No Known Activations