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

    Neuronpedia

    INDEX
    Explanations

    iff

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .tom
    -0.07
    ideos
    -0.07
    低于
    -0.07
    Ⲙ
    -0.07
    降到
    -0.07
     abol
    -0.07
    抵
    -0.07
    -maker
    -0.07
     deter
    -0.07
     smo
    -0.07
    POSITIVE LOGITS
    ys
    0.08
     Harley
    0.07
     landing
    0.07
    沙龙
    0.07
     bass
    0.07
    le
    0.06
     Dal
    0.06
     pillar
    0.06
     StringBuilder
    0.06
    (/
    0.06
    Act Density 0.002%

    No Known Activations