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

    Neuronpedia

    INDEX
    Explanations

    Furthermore

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    07
    -0.07
     Hüs
    -0.07
     Nail
    -0.07
    ’t
    -0.06
    preci
    -0.06
    08
    -0.06
     stolen
    -0.06
     reputation
    -0.06
     business
    -0.06
    't
    -0.06
    POSITIVE LOGITS
     Furthermore
    0.09
    Furthermore
    0.08
    ुन
    0.08
    KER
    0.07
    XR
    0.07
    venir
    0.07
    tere
    0.07
    ถาม
    0.07
     salir
    0.07
    атор
    0.07
    Act Density 0.012%

    No Known Activations