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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    $array
    -0.06
    คราม
    -0.06
     haul
    -0.06
     ファ
    -0.06
     proč
    -0.06
     hizmet
    -0.06
     equipo
    -0.06
    �
    -0.06
    ')
↵
    -0.05
    six
    -0.05
    POSITIVE LOGITS
     historia
    0.07
     partly
    0.07
    μμε
    0.07
     ElementType
    0.07
     pastry
    0.07
    (copy
    0.07
     wilderness
    0.06
    érieur
    0.06
    _exempt
    0.06
    _ME
    0.06
    Act Density 0.000%

    No Known Activations