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

    Neuronpedia

    INDEX
    Explanations

    formulas and code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ัป
    0.47
    彠
    0.44
    룔
    0.42
    𒊑
    0.42
    Logs
    0.41
    BERS
    0.41
    ติด
    0.40
    贰
    0.39
    裹
    0.39
    責任
    0.38
    POSITIVE LOGITS
     Pert
    0.45
     ideale
    0.41
     austral
    0.39
     Austr
    0.36
    әү
    0.36
     jama
    0.36
     emerge
    0.35
    niches
    0.35
     varia
    0.34
    Pert
    0.34
    Act Density 0.000%

    No Known Activations