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

    Neuronpedia

    INDEX
    Explanations

    988 suicide hotline

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    清
    0.40
     Hers
    0.39
     Hercules
    0.37
    Hers
    0.36
     antisocial
    0.35
     zicht
    0.35
     Zol
    0.34
    Zoo
    0.34
     Зо
    0.34
    frog
    0.33
    POSITIVE LOGITS
    grained
    0.37
    tega
    0.36
     grained
    0.35
    Ei
    0.34
    яр
    0.34
    ᡤ
    0.34
     lauren
    0.33
     purus
    0.33
    Cog
    0.33
     pier
    0.33
    Act Density 0.007%

    No Known Activations