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

    Neuronpedia

    INDEX
    Explanations

    inequalities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pubblic
    -0.08
     pública
    -0.08
     सार्वजनिक
    -0.08
     Bulg
    -0.07
     public
    -0.07
    (cert
    -0.07
     Public
    -0.07
    /net
    -0.07
     giro
    -0.07
    :");
↵
    -0.07
    POSITIVE LOGITS
    Worst
    0.09
     darkest
    0.09
     restrict
    0.09
     worse
    0.08
     peor
    0.08
     worst
    0.08
     deepest
    0.08
     profondeur
    0.08
    aziri
    0.08
     darkness
    0.08
    Act Density 0.057%

    No Known Activations