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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rollout
    -0.07
    crop
    -0.06
    _version
    -0.06
     fol
    -0.06
     Say
    -0.06
    fly
    -0.06
     seal
    -0.05
     wer
    -0.05
     bees
    -0.05
    限制
    -0.05
    POSITIVE LOGITS
    cmpeq
    0.07
     않고
    0.07
    ominated
    0.07
    &utm
    0.07
     yaz
    0.06
     ruthless
    0.06
     uluslararası
    0.06
    ní
    0.06
     totalPages
    0.06
    odef
    0.06
    Act Density 0.000%

    No Known Activations