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

    Neuronpedia

    INDEX
    Explanations

    Object properties/fields

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     όλ
    0.99
     nepř
    0.99
    kaç
    0.98
     solamente
    0.93
    琤
    0.92
     kurang
    0.92
    à
    0.91
    minutes
    0.90
     otten
    0.90
     empez
    0.89
    POSITIVE LOGITS
    AM
    0.91
     fateful
    0.82
     conception
    0.82
    IO
    0.76
     location
    0.75
     fragilis
    0.75
    .
    0.75
    OS
    0.74
     assignment
    0.74
     crafts
    0.73
    Act Density 0.000%

    No Known Activations