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

    Neuronpedia

    INDEX
    Explanations

    layouts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    upert
    -0.07
    -scale
    -0.07
    artisan
    -0.07
    xf
    -0.07
    ским
    -0.07
    еч
    -0.07
     eb
    -0.06
     Club
    -0.06
    雨
    -0.06
     island
    -0.06
    POSITIVE LOGITS
    .poll
    0.07
    -origin
    0.07
    =''
    0.07
     abras
    0.07
    폽
    0.07
    (low
    0.07
     Harr
    0.07
    𬸦
    0.06
    Fd
    0.06
     mentre
    0.06
    Act Density 0.036%

    No Known Activations