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

    Neuronpedia

    INDEX
    Explanations

    ^

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Olive
    -0.08
    足迹
    -0.08
    raf
    -0.07
    𝖐
    -0.07
    àng
    -0.07
    绡
    -0.07
     babe
    -0.07
     hair
    -0.07
     Plants
    -0.07
     calves
    -0.07
    POSITIVE LOGITS
    precio
    0.08
     Equity
    0.07
    says
    0.07
    Ń
    0.07
    ῟
    0.07
    班级
    0.07
    Bl
    0.06
    radius
    0.06
     combines
    0.06
    ꀰ
    0.06
    Act Density 0.000%

    No Known Activations