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

    Neuronpedia

    INDEX
    Explanations

    Code/technical text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    MAN
    -0.08
    锢
    -0.07
    ную
    -0.07
     Putin
    -0.07
    处处
    -0.06
    դ
    -0.06
     SpaceX
    -0.06
    possible
    -0.06
    phy
    -0.06
    endereco
    -0.06
    POSITIVE LOGITS
     поч
    0.07
    镵
    0.07
    机油
    0.07
    �
    0.06
    CompatActivity
    0.06
     obligated
    0.06
    gorit
    0.06
    伊利
    0.06
     infr
    0.06
    がかか
    0.06
    Act Density 0.002%

    No Known Activations