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

    Neuronpedia

    INDEX
    Explanations

    OPSIS

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cl
    -0.07
    言って
    -0.06
     Carl
    -0.06
    Normalization
    -0.06
     drawers
    -0.06
    _VAL
    -0.06
    ження
    -0.06
    Š
    -0.06
     bare
    -0.06
     '../../
    -0.06
    POSITIVE LOGITS
    فی
    0.06
    ома
    0.06
    Genesis
    0.06
    Woman
    0.06
     �
    0.06
     leftover
    0.06
    layout
    0.06
    ublish
    0.06
    idl
    0.06
     Jenna
    0.06
    Act Density 0.008%

    No Known Activations