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

    Neuronpedia

    INDEX
    Explanations

    variable and proportional

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    cd
    0.39
     Lof
    0.38
     transcend
    0.37
    Q
    0.37
    ButtonStyle
    0.37
    profession
    0.37
     cd
    0.36
    Timer
    0.36
     productId
    0.35
     Pantheon
    0.35
    POSITIVE LOGITS
     VARIABLE
    0.59
     Variable
    0.53
     variable
    0.52
     सग
    0.47
    VARIABLE
    0.46
    rotnie
    0.45
    しない
    0.43
     variável
    0.43
    Variable
    0.43
     variabile
    0.42
    Act Density 0.000%

    No Known Activations