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

    Neuronpedia

    INDEX
    Explanations

    minimize or maximize

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -
    0.47
    させて
    0.45
    insert
    0.42
    salary
    0.41
    に
    0.41
    ཋ
    0.40
    X
    0.39
    drop
    0.39
    tit
    0.39
     inflate
    0.38
    POSITIVE LOGITS
     cuales
    0.46
     emphasised
    0.45
     custod
    0.44
     decisão
    0.42
    цию
    0.42
     ಸೂ
    0.42
    婫
    0.42
    createdBy
    0.41
    संधान
    0.41
     terão
    0.41
    Act Density 0.002%

    No Known Activations