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

    Neuronpedia

    INDEX
    Explanations

    section or explanatory titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ákat
    0.35
    clientes
    0.35
    cursos
    0.34
    𝚣
    0.34
    𝚓
    0.33
    нить
    0.32
    количество
    0.32
    inizin
    0.32
    ндары
    0.31
    fonction
    0.31
    POSITIVE LOGITS
     =
    0.44
     (
    0.44
     |
    0.43
     &
    0.42
     {
    0.41
     Summary
    0.40
     Details
    0.40
     :
    0.39
     -
    0.39
     Key
    0.38
    Act Density 1.138%

    No Known Activations