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

    Neuronpedia

    INDEX
    Explanations

    acronyms with abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SpacerItem
    0.28
    রূপ
    0.27
     răng
    0.26
     negligent
    0.26
     getDescription
    0.26
     तर्क
    0.25
     Süden
    0.25
    <unused12>
    0.25
    jLabel
    0.25
     árvore
    0.25
    POSITIVE LOGITS
    IA
    0.44
    AC
    0.43
    و
    0.42
    AS
    0.40
    ER
    0.40
    IS
    0.39
    I
    0.38
    IP
    0.38
    Q
    0.38
    IC
    0.38
    Act Density 1.410%

    No Known Activations