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

    Neuronpedia

    INDEX
    Explanations

    decline

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    emos
    -0.07
     WATER
    -0.07
     пользоват
    -0.07
    pher
    -0.07
     有
    -0.07
     towing
    -0.06
     wer
    -0.06
     mét
    -0.06
     naked
    -0.06
    et
    -0.06
    POSITIVE LOGITS
     decline
    0.13
     declining
    0.11
     declines
    0.10
     declined
    0.09
    cline
    0.08
    line
    0.08
    :
    0.08
     سین
    0.08
    sdale
    0.07
     EINVAL
    0.07
    Act Density 0.007%

    No Known Activations