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

    Neuronpedia

    INDEX
    Explanations

    Abstract

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tarafından
    0.53
    erical
    0.51
     tych
    0.48
     clothe
    0.47
     aé
    0.47
     automatis
    0.46
     acides
    0.45
     pourra
    0.45
     abuso
    0.44
     часы
    0.44
    POSITIVE LOGITS
    Abstract
    0.46
     Abstract
    0.45
     NotImplemented
    0.44
    د
    0.44
    Q
    0.44
    abstract
    0.44
    s
    0.44
    ABSTRACT
    0.43
    ν
    0.43
     Stateful
    0.42
    Act Density 0.004%

    No Known Activations