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

    Neuronpedia

    INDEX
    Explanations

    -weight

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    镏
    -0.07
    近三年
    -0.07
    .ax
    -0.07
     Cab
    -0.07
    amaha
    -0.07
    庥
    -0.06
    imonial
    -0.06
    톱
    -0.06
     poke
    -0.06
     runaway
    -0.06
    POSITIVE LOGITS
     Aware
    0.08
     currency
    0.07
     Nat
    0.07
    策略
    0.07
    ValuePair
    0.07
    .Vert
    0.07
    Class
    0.07
     Commit
    0.07
    记住
    0.07
    郑重
    0.07
    Act Density 0.002%

    No Known Activations