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

    Neuronpedia

    INDEX
    Explanations

    Modification or improvement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    aclass
    -0.07
    �
    -0.06
     affordability
    -0.06
     �
    -0.06
     abrir
    -0.06
     špat
    -0.06
     continuar
    -0.06
     "]"
    -0.06
    _asc
    -0.06
    brains
    -0.06
    POSITIVE LOGITS
    kind
    0.06
    _CITY
    0.06
     Quote
    0.06
     ValueType
    0.06
     Ley
    0.06
    reece
    0.06
    原
    0.06
    .Tile
    0.05
     مات
    0.05
    review
    0.05
    Act Density 0.019%

    No Known Activations