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

    Neuronpedia

    INDEX
    Explanations

    factors

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     WCHAR
    -0.07
    ідно
    -0.07
    evi
    -0.06
     hơn
    -0.06
     fuer
    -0.06
     farm
    -0.06
    uento
    -0.06
    jí
    -0.06
    SEMB
    -0.06
    шая
    -0.06
    POSITIVE LOGITS
     Harvard
    0.07
     soluble
    0.06
     macOS
    0.06
    _AB
    0.06
    (nd
    0.06
     magnesium
    0.06
     conspic
    0.06
     STYLE
    0.05
     пре
    0.05
     Bedford
    0.05
    Act Density 0.031%

    No Known Activations