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

    Neuronpedia

    INDEX
    Explanations

    -box

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    盘点
    -0.08
    ابة
    -0.07
    孩童
    -0.07
    _clr
    -0.07
     pkg
    -0.07
    ש
    -0.07
     MPs
    -0.07
    setq
    -0.06
     Pavel
    -0.06
     braking
    -0.06
    POSITIVE LOGITS
    .debugLine
    0.06
    relation
    0.06
    ⤵
    0.06
    ложения
    0.06
    entities
    0.06
    jectories
    0.06
     results
    0.06
    資源
    0.06
     transmission
    0.06
     abbiamo
    0.06
    Act Density 0.000%

    No Known Activations