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

    Neuronpedia

    INDEX
    Explanations

    roles in relationships or transactions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ４
    0.41
    <unused2047>
    0.40
    чны
    0.39
     vibhav
    0.39
    𝒞
    0.38
    zPosition
    0.38
    monospace
    0.38
    жек
    0.38
    روط
    0.38
    блема
    0.37
    POSITIVE LOGITS
    in
    0.49
    ed
    0.48
    ור
    0.46
    en
    0.44
    ’
    0.41
    ון
    0.41
    ad
    0.39
     on
    0.38
     or
    0.38
    m
    0.38
    Act Density 0.112%

    No Known Activations