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

    Neuronpedia

    INDEX
    Explanations

    HTTPS instead

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    fluid
    0.52
    сы
    0.48
     fluids
    0.48
    берг
    0.47
    cular
    0.46
    servicio
    0.46
    leton
    0.45
    solving
    0.45
    regular
    0.44
    koliko
    0.44
    POSITIVE LOGITS
    信息
    0.43
     escaped
    0.43
     Bias
    0.42
    <start_of_image>
    0.41
     tán
    0.41
     blaster
    0.40
     Ford
    0.40
     Fitz
    0.40
     Firefox
    0.40
     goat
    0.40
    Act Density 0.002%

    No Known Activations