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

    Neuronpedia

    INDEX
    Explanations

    out

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hazards
    -0.08
    农业科技
    -0.07
    涅
    -0.07
    �
    -0.07
    因地制
    -0.07
    診
    -0.06
     trực
    -0.06
     �
    -0.06
    ровер
    -0.06
    ibraltar
    -0.06
    POSITIVE LOGITS
    램
    0.07
    #\
    0.06
    钏
    0.06
    !!!!!
    0.06
     kró
    0.06
     hangs
    0.06
     '"';↵
    0.06
     Kang
    0.06
    Bạn
    0.06
     Shall
    0.06
    Act Density 0.008%

    No Known Activations