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

    Neuronpedia

    INDEX
    Explanations

    by

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sevent
    -0.07
    Це
    -0.07
     lun
    -0.07
    Gen
    -0.07
    toHaveBeenCalled
    -0.06
    .Site
    -0.06
     Squadron
    -0.06
     ngOnDestroy
    -0.06
     виконав
    -0.06
    [opt
    -0.06
    POSITIVE LOGITS
    ammer
    0.07
    ning
    0.07
    sim
    0.07
     регуляр
    0.06
    verts
    0.06
    дается
    0.06
     arasında
    0.06
    сии
    0.06
     ­
    0.06
    の
    0.06
    Act Density 0.008%

    No Known Activations