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

    Neuronpedia

    INDEX
    Explanations

    else or return

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OLOG
    0.46
    ﺨ
    0.41
    NORM
    0.41
     cosidd
    0.41
    Pressure
    0.40
    Acet
    0.40
    עת
    0.39
     NOTICE
    0.39
    שו
    0.39
    خيص
    0.39
    POSITIVE LOGITS
    else
    0.55
     else
    0.52
     otherwise
    0.52
    iteiten
    0.47
    íes
    0.45
     तत्वा
    0.45
     Otherwise
    0.45
    iad
    0.45
    vc
    0.43
     thriving
    0.43
    Act Density 0.094%

    No Known Activations