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

    Neuronpedia

    INDEX
    Explanations

    operator precedence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     offs
    -0.08
     دين
    -0.07
    Inactive
    -0.06
    CHO
    -0.06
    decay
    -0.06
     πολύ
    -0.06
     ＼:
    -0.06
     zug
    -0.06
    ctp
    -0.06
     Moreno
    -0.06
    POSITIVE LOGITS
    .Names
    0.08
     Ange
    0.07
    わたし
    0.07
     Brad
    0.07
     Phoenix
    0.06
     عاما
    0.06
    Phoenix
    0.06
    电脑
    0.06
     доме
    0.06
     configFile
    0.06
    Act Density 0.014%

    No Known Activations