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

    Neuronpedia

    INDEX
    Explanations

    code arguments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    CAT
    0.75
     المركزي
    0.74
    cent
    0.71
    kaart
    0.71
     cent
    0.70
    getClient
    0.69
    centroid
    0.68
    global
    0.68
     centra
    0.68
    CRED
    0.68
    POSITIVE LOGITS
    ར
    0.63
    バード
    0.60
    stm
    0.60
    റൽ
    0.59
    alah
    0.55
    ኢ
    0.55
     contested
    0.55
     ưu
    0.55
     वाला
    0.55
    stom
    0.55
    Act Density 0.173%

    No Known Activations