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

    Neuronpedia

    INDEX
    Explanations

    Code/identifiers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    原油
    -0.07
     srv
    -0.07
     Tipo
    -0.07
    农作物
    -0.06
    割
    -0.06
    أش
    -0.06
    国企
    -0.06
    指令
    -0.06
     statically
    -0.06
    闰
    -0.06
    POSITIVE LOGITS
    /preferences
    0.07
    ochond
    0.07
    ระว
    0.07
     Contemporary
    0.06
    Ne
    0.06
    _clients
    0.06
    eous
    0.06
    ierge
    0.06
     Może
    0.06
    _models
    0.06
    Act Density 1.014%

    No Known Activations