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

    Neuronpedia

    INDEX
    Explanations

    support and opportunities for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     are
    0.29
     v
    0.22
     c
    0.21
     sono
    0.20
     Spider
    0.20
     Century
    0.20
    abolic
    0.20
     avez
    0.19
     GU
    0.19
     Vera
    0.19
    POSITIVE LOGITS
    于
    0.30
    ให้กับ
    0.28
     для
    0.26
     براي
    0.25
     kepada
    0.25
    ForSettings
    0.25
    សម្រាប់ការ
    0.24
    ле
    0.24
    для
    0.24
     للم
    0.23
    Act Density 0.693%

    No Known Activations