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

    Neuronpedia

    INDEX
    Explanations

    pos

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Erf
    -0.07
    대학
    -0.07
    mh
    -0.07
    .perform
    -0.07
    מינ
    -0.07
     evolve
    -0.07
    xAA
    -0.07
     Americas
    -0.07
    英格
    -0.07
    	payload
    -0.07
    POSITIVE LOGITS
    洗净
    0.08
     Armenian
    0.07
    废弃物
    0.07
    users
    0.07
     peas
    0.07
    胆固
    0.07
     disfr
    0.07
     strut
    0.07
     braces
    0.07
    auto
    0.07
    Act Density 0.009%

    No Known Activations