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

    Neuronpedia

    INDEX
    Explanations

    go to the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     scor
    1.28
     augment
    1.25
    t
    1.25
    sprach
    1.23
    fasta
    1.22
    नावश्यक
    1.20
     searing
    1.19
    ieben
    1.17
    y
    1.17
    k
    1.16
    POSITIVE LOGITS
    Yeah
    1.51
    »،
    1.37
    ты
    1.32
    ە
    1.32
    」、
    1.30
    야
    1.27
    딩
    1.26
    леты
    1.23
    ﺢ
    1.23
    真正的
    1.21
    Act Density 0.045%

    No Known Activations