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

    Neuronpedia

    INDEX
    Explanations

    help you with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     всегда
    0.56
     always
    0.54
     aina
    0.49
     selalu
    0.47
     zawsze
    0.47
     ALWAYS
    0.46
    一直
    0.45
    Always
    0.45
     sempre
    0.44
     Always
    0.44
    POSITIVE LOGITS
     calendário
    0.40
    利亚
    0.39
    elve
    0.37
    <u>
    0.37
     Pu
    0.37
    gauge
    0.37
    ︿
    0.37
    Lst
    0.37
     Vend
    0.36
    riven
    0.36
    Act Density 0.000%

    No Known Activations