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

    Neuronpedia

    INDEX
    Explanations

    foundation, pretrained, Face, feedback, symmetric

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Еще
    0.68
    heten
    0.64
    0.63
    ného
    0.55
     ResponseEntity
    0.55
    。",
    0.55
    Hepinize
    0.54
     ",
    0.52
     organising
    0.52
     `,
    0.52
    POSITIVE LOGITS
    ↵
    1.15
    z
    0.75
    ل
    0.69
     будут
    0.68
    ಗಳನ್ನು
    0.64
    :
    0.63
    ת
    0.63
    প্রাপ্ত
    0.63
    ك
    0.63
    atrice
    0.62
    Act Density 0.000%

    No Known Activations