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

    Neuronpedia

    INDEX
    Explanations

    at a certain rate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PanelVisual
    0.45
    ος
    0.43
    itipi
    0.43
     ಪೂರ್ವ
    0.42
    GBuf
    0.41
    FreeFlag
    0.41
     balcon
    0.41
    豢
    0.41
    Hence
    0.41
     වන
    0.40
    POSITIVE LOGITS
     an
    0.46
     a
    0.41
     Classes
    0.38
     Rage
    0.38
     constant
    0.37
     dan
    0.37
     rage
    0.36
     RMS
    0.36
     Opp
    0.36
    -
    0.35
    Act Density 0.019%

    No Known Activations