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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    nombre
    -0.07
     tbsp
    -0.07
     problémy
    -0.07
    ип
    -0.07
     твор
    -0.07
    りに
    -0.06
    เช
    -0.06
    iko
    -0.06
     größ
    -0.06
     près
    -0.06
    POSITIVE LOGITS
     Wood
    0.07
    =forms
    0.06
    =r
    0.06
    =DB
    0.06
     (--
    0.06
    紅
    0.06
    :b
    0.06
     Herr
    0.06
    :end
    0.06
     Mapper
    0.06
    Act Density 0.098%

    No Known Activations