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

    Neuronpedia

    INDEX
    Explanations

    red ring and SAMHSA helpline

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lap
    0.45
     Bouchard
    0.40
     Lach
    0.39
     laps
    0.39
    अन
    0.39
     Lap
    0.38
     shark
    0.38
    Lap
    0.38
     brazil
    0.37
     തര
    0.36
    POSITIVE LOGITS
    sa
    0.37
    Blitz
    0.37
     Sa
    0.36
     Blitz
    0.36
    uski
    0.35
    สา
    0.34
    nega
    0.34
    Sa
    0.33
     Pho
    0.33
     Ju
    0.32
    Act Density 0.007%

    No Known Activations