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

    Neuronpedia

    INDEX
    Explanations

    lists

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    871
    -0.07
    及其
    -0.06
    ValueType
    -0.06
    CPF
    -0.06
     khỏi
    -0.06
     sentido
    -0.06
     commissioner
    -0.06
    Processor
    -0.06
    	Vector
    -0.06
    MV
    -0.06
    POSITIVE LOGITS
     уд
    0.06
    ation
    0.06
    /window
    0.06
    essel
    0.06
    otu
    0.06
    lox
    0.06
    eof
    0.06
    oriasis
    0.06
    olem
    0.06
     Ré
    0.06
    Act Density 0.033%

    No Known Activations