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

    Neuronpedia

    INDEX
    Explanations

    placeholder

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     BIOS
    -0.08
     Ny
    -0.07
     Lé
    -0.07
     Saul
    -0.07
    ेज
    -0.07
    encana
    -0.07
     मिले
    -0.07
     legen
    -0.07
    -0.07
     reporte
    -0.07
    POSITIVE LOGITS
     placeholders
    0.14
     обознач
    0.10
    _placeholder
    0.10
     Placeholder
    0.10
     replacements
    0.10
     sustitu
    0.10
     SUBSTITUTE
    0.10
    Placeholder
    0.10
    .placeholder
    0.09
     placeholder
    0.09
    Act Density 0.012%
    No Known Activations