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

    Neuronpedia

    INDEX
    Explanations

    sit down

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .
    0.77
    𝐊
    0.64
    Mont
    0.62
    Identification
    0.59
    、（
    0.59
    KET
    0.58
    liste
    0.58
    3
    0.57
    Keefe
    0.57
    PORT
    0.56
    POSITIVE LOGITS
    at
    0.75
    τα
    0.75
    ید
    0.68
    აფ
    0.63
    вой
    0.62
    h
    0.62
    il
    0.61
     ngồi
    0.60
     sentado
    0.60
     asiento
    0.59
    Act Density 0.007%

    No Known Activations