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

    Neuronpedia

    INDEX
    Explanations

    mental health resources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nextNode
    0.39
    <start_of_turn>
    0.36
    waż
    0.36
    ților
    0.35
    उ
    0.34
    Hur
    0.34
    ｉ
    0.33
    ﻴ
    0.33
     किस
    0.33
    ित्र
    0.33
    POSITIVE LOGITS
     وعلى
    1.05
     behalf
    0.92
     occasion
    0.55
     occasions
    0.53
     základě
    0.53
     basis
    0.50
     этапе
    0.43
     apps
    0.43
     Grundlage
    0.42
     ticks
    0.41
    Act Density 0.006%

    No Known Activations