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

    Neuronpedia

    INDEX
    Explanations

    Scientific paper introductions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    annes
    -0.07
     havoc
    -0.07
    .colorbar
    -0.07
    Such
    -0.07
     hm
    -0.06
    若
    -0.06
    licting
    -0.06
     Context
    -0.06
     xb
    -0.06
    Via
    -0.06
    POSITIVE LOGITS
    クラブ
    0.08
     Gründe
    0.07
     билет
    0.07
    增资
    0.07
    _DAYS
    0.07
    _processed
    0.07
    下班
    0.07
     sigu
    0.07
    Absolute
    0.07
    _MARGIN
    0.06
    Act Density 0.000%

    No Known Activations