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

    Neuronpedia

    INDEX
    Explanations

    gathering and initialization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    src
    0.49
    riven
    0.49
    рою
    0.49
    driven
    0.47
    en
    0.47
    irán
    0.47
    t
    0.47
    рав
    0.46
    et
    0.46
    т
    0.46
    POSITIVE LOGITS
     *}\
    0.54
     Pandas
    0.52
     modify
    0.52
     ظِلِّ
    0.52
     amikor
    0.51
    <unused2>
    0.51
     Modify
    0.50
    OLOGY
    0.50
    ជ្រ
    0.49
     Hoodie
    0.49
    Act Density 0.001%

    No Known Activations