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

    Neuronpedia

    INDEX
    Explanations

    after

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Moder
    -0.07
    magnitude
    -0.06
     rend
    -0.06
     gad
    -0.06
     bleak
    -0.06
     Thesis
    -0.06
     anything
    -0.05
    chematic
    -0.05
    /OR
    -0.05
    .only
    -0.05
    POSITIVE LOGITS
     البل
    0.07
     which
    0.07
     baseUrl
    0.07
    EU
    0.07
    Mitch
    0.07
     `"
    0.07
     tehdy
    0.07
    Jos
    0.06
    npj
    0.06
    []):
    0.06
    Act Density 0.000%

    No Known Activations