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

    Neuronpedia

    INDEX
    Explanations

    academic/technical texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Colorado
    -0.07
     suất
    -0.07
     scop
    -0.07
    -element
    -0.06
     europ
    -0.06
    哪种
    -0.06
    טופ
    -0.06
     Southern
    -0.06
    cent
    -0.06
     VE
    -0.06
    POSITIVE LOGITS
     lifted
    0.07
    libraries
    0.07
     Linked
    0.07
    ƅ
    0.07
    图表
    0.07
    转变
    0.07
    框架
    0.07
     linen
    0.06
    ilder
    0.06
    ramid
    0.06
    Act Density 0.332%

    No Known Activations