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

    Neuronpedia

    INDEX
    Explanations

    functions and their purpose

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    LE
    0.75
    rin
    0.75
    I
    0.73
    rina
    0.71
    াতাড়ি
    0.69
    ya
    0.68
    TINGS
    0.67
    3
    0.67
    时间的
    0.65
    蜢
    0.65
    POSITIVE LOGITS
    ות
    1.05
     functions
    1.00
     myFunction
    1.00
    ہ
    0.99
     funzione
    0.98
    ק
    0.95
    ור
    0.94
    ک
    0.93
     funcion
    0.92
     fonction
    0.92
    Act Density 0.078%

    No Known Activations