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

    Neuronpedia

    INDEX
    Explanations

    tbody

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     إح
    -0.07
    埇
    -0.07
    והר
    -0.07
    औ
    -0.07
     BufferedImage
    -0.06
     refrain
    -0.06
    orphic
    -0.06
    쏩
    -0.06
    开会
    -0.06
    Yet
    -0.06
    POSITIVE LOGITS
    进了
    0.07
    skin
    0.07
    Ruby
    0.07
    Segments
    0.07
    应收
    0.07
    _INPUT
    0.07
     noble
    0.07
     jets
    0.07
     sector
    0.07
     trabajo
    0.07
    Act Density 0.000%

    No Known Activations