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

    Neuronpedia

    INDEX
    Explanations

    ind

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     breaches
    -0.07
     visit
    -0.07
    化学品
    -0.07
    ㄥ
    -0.07
     dac
    -0.07
    _fa
    -0.07
    融创
    -0.06
     Ms
    -0.06
    细分
    -0.06
    𝚏
    -0.06
    POSITIVE LOGITS
     Warm
    0.07
     platinum
    0.07
    _scalar
    0.07
    RANDOM
    0.06
    ‒
    0.06
     Saints
    0.06
    illed
    0.06
     Making
    0.06
    ümüz
    0.06
     Intr
    0.06
    Act Density 0.000%

    No Known Activations