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

    Neuronpedia

    INDEX
    Explanations

    computer-generated text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    jec
    -0.30
    棺
    -0.29
    TypeInfo
    -0.27
    æīĵæ³ķ
    -0.26
    mediate
    -0.26
    _typ
    -0.25
    Bindable
    -0.25
     typical
    -0.25
     mediation
    -0.25
    med
    -0.25
    POSITIVE LOGITS
    æĬĬ她
    0.30
    对她
    0.27
     Towers
    0.27
    éĤ£éº¼
    0.27
    åijĬè¯ī她
    0.25
     ATS
    0.25
    éĢļè¿ĩ对
    0.25
    åIJĮæĻĤ
    0.25
     Who
    0.24
     WHO
    0.24
    Act Density 0.012%

    No Known Activations