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

    Neuronpedia

    INDEX
    Explanations

    Code/technical documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     floating
    -0.07
    cel
    -0.07
     spou
    -0.07
    Giving
    -0.07
     my
    -0.07
    Expand
    -0.07
    cent
    -0.06
     Discipline
    -0.06
    GRES
    -0.06
    cube
    -0.06
    POSITIVE LOGITS
    追
    0.07
    -v
    0.07
     harmless
    0.07
     hodně
    0.07
     YYYY
    0.06
     allegedly
    0.06
     controversy
    0.06
    ीछ
    0.06
     retailer
    0.06
     lineback
    0.06
    Act Density 0.000%

    No Known Activations