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

    Neuronpedia

    INDEX
    Explanations

    code/data arrays

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     food
    -0.07
    _Template
    -0.07
    _pl
    -0.07
     arreglo
    -0.07
    Ep
    -0.06
     hry
    -0.06
    =T
    -0.06
     sorun
    -0.06
     método
    -0.06
     nutrition
    -0.06
    POSITIVE LOGITS
     ZEND
    0.06
    گونه
    0.06
    α
    0.06
    pmat
    0.06
    gili
    0.06
     storms
    0.06
    -com
    0.06
    prus
    0.06
     Exact
    0.06
     chắc
    0.06
    Act Density 0.041%

    No Known Activations