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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mú
    -0.07
     Gand
    -0.06
    Earth
    -0.06
     turning
    -0.06
     Kush
    -0.06
     části
    -0.06
    \Column
    -0.06
     směrem
    -0.06
     Tuesday
    -0.06
     Humph
    -0.06
    POSITIVE LOGITS
     goalkeeper
    0.07
    iconductor
    0.07
    …"↵↵
    0.06
     digital
    0.06
    jual
    0.06
    oked
    0.06
    icone
    0.06
     Υ
    0.06
    意义
    0.06
     dále
    0.06
    Act Density 0.000%

    No Known Activations