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

    Neuronpedia

    INDEX
    Explanations

    legal appeals

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    UILD
    -0.07
    approve
    -0.07
    経
    -0.07
    SSI
    -0.07
     borrow
    -0.06
    ══
    -0.06
    iting
    -0.06
     demande
    -0.06
    44
    -0.06
     Eye
    -0.06
    POSITIVE LOGITS
     samozřejmě
    0.07
     accessories
    0.06
     pollution
    0.06
     короб
    0.06
    贝
    0.06
     Ends
    0.06
     모
    0.06
    .ax
    0.06
    _NOW
    0.06
    .unsqueeze
    0.06
    Act Density 0.010%

    No Known Activations