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

    Neuronpedia

    INDEX
    Explanations

    6

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tl
    -0.07
     LL
    -0.07
     Cah
    -0.07
     Blades
    -0.07
     tras
    -0.06
    Когда
    -0.06
    Kick
    -0.06
    aların
    -0.06
    비스
    -0.06
    Face
    -0.06
    POSITIVE LOGITS
    processable
    0.07
     rapper
    0.07
    五月
    0.06
     juxtap
    0.06
     modern
    0.06
     reign
    0.06
     Marriott
    0.06
     جه
    0.06
    bishop
    0.06
    (segment
    0.06
    Act Density 0.003%

    No Known Activations