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

    Neuronpedia

    INDEX
    Explanations

    numbers or lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ین
    0.49
     Cá
    0.49
     Westminster
    0.45
    ተ
    0.44
    رخ
    0.44
     adimensional
    0.44
    áin
    0.43
     Más
    0.43
    奘
    0.42
    āl
    0.42
    POSITIVE LOGITS
     रेलवे
    0.54
    ас
    0.54
     depositing
    0.51
     suppressing
    0.49
     cercando
    0.49
    Encode
    0.47
     poniendo
    0.47
     Railway
    0.46
    ግሎ
    0.46
    queous
    0.45
    Act Density 0.000%

    No Known Activations