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

    Neuronpedia

    INDEX
    Explanations

    local installation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ciertos
    0.54
    㐰
    0.47
     дистан
    0.47
     ciclos
    0.46
     vegetales
    0.46
     tenis
    0.45
     relacionados
    0.45
    穼
    0.44
    াক্তন
    0.44
    Кроме
    0.43
    POSITIVE LOGITS
    m
    0.57
    ville
    0.52
    OD
    0.50
    ms
    0.50
    ep
    0.48
    ga
    0.47
    group
    0.47
     DNA
    0.47
    od
    0.47
    ec
    0.46
    Act Density 0.001%

    No Known Activations