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

    Neuronpedia

    INDEX
    Explanations

    ropo

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rent
    -0.68
    rok
    -0.65
    BarButtonItem
    -0.58
    jor
    -0.56
    ground
    -0.53
    rote
    -0.52
    kn
    -0.52
    ropol
    -0.52
    roe
    -0.52
    bind
    -0.50
    POSITIVE LOGITS
    SharedCtor
    0.71
    ergies
    0.70
    soever
    0.69
     Lightboxes
    0.62
    gonic
    0.60
     externi
    0.60
     myſelf
    0.60
     himo
    0.58
    rália
    0.57
    seamnă
    0.57
    Act Density 0.146%

    No Known Activations