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

    Neuronpedia

    INDEX
    Explanations

    Supporting/opposing something

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tricks
    -0.09
     MATLAB
    -0.09
     Tricks
    -0.08
     trick
    -0.08
     Trick
    -0.08
     mágico
    -0.08
     बनाया
    -0.08
     mobi
    -0.07
     PID
    -0.07
     Aula
    -0.07
    POSITIVE LOGITS
     advocating
    0.22
     advocated
    0.18
     advocacy
    0.17
     advocate
    0.17
     advocates
    0.16
    倡
    0.15
     Advoc
    0.15
     Advocacy
    0.14
     outspoken
    0.13
     vehe
    0.13
    Act Density 0.199%

    No Known Activations