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

    Neuronpedia

    INDEX
    Explanations

    gray

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .abstract
    -0.07
     child
    -0.07
    ,alpha
    -0.07
     spiritually
    -0.06
     đạo
    -0.06
    英語
    -0.06
    ála
    -0.06
    ryptography
    -0.06
    SCO
    -0.06
    Aspect
    -0.06
    POSITIVE LOGITS
     Grey
    0.07
    .Priority
    0.06
     wear
    0.06
     Hum
    0.06
     мой
    0.06
    .MiddleRight
    0.06
     drawback
    0.06
     parks
    0.06
    :NSUTF
    0.06
    .Ret
    0.06
    Act Density 0.001%

    No Known Activations