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

    Neuronpedia

    INDEX
    Explanations

    sakya

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     glandular
    0.52
     gland
    0.51
     gobl
    0.50
     prost
    0.49
     видел
    0.47
     horizonte
    0.47
     assistants
    0.47
     cicat
    0.47
     bombs
    0.46
     divisive
    0.46
    POSITIVE LOGITS
    n
    0.73
    il
    0.70
    ir
    0.56
    ar
    0.51
    ac
    0.51
    sekten
    0.51
    i
    0.50
    er
    0.49
    ن
    0.49
    al
    0.48
    Act Density 0.000%

    No Known Activations