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

    Neuronpedia

    INDEX
    Explanations

    explaining goals and impact

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     catalyst
    0.54
    fecha
    0.51
    -
    0.51
     canto
    0.50
     voi
    0.49
    kova
    0.49
    י
    0.48
     egyptian
    0.48
     Pode
    0.48
    ian
    0.47
    POSITIVE LOGITS
    㸸
    0.44
     хрони
    0.42
    を経て
    0.41
     resTmp
    0.41
    ńcz
    0.41
    エク
    0.40
    䧣
    0.39
    엑
    0.39
    fitness
    0.38
    Fitness
    0.38
    Act Density 0.002%

    No Known Activations