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

    Neuronpedia

    INDEX
    Explanations

    ="

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	Message
    -0.07
    .State
    -0.06
    POWER
    -0.06
    Imm
    -0.06
     titulo
    -0.06
     должно
    -0.06
     nov
    -0.06
    .correct
    -0.06
    Kate
    -0.06
     Early
    -0.06
    POSITIVE LOGITS
     guit
    0.07
    ΕΧ
    0.06
     Да
    0.06
    .ticket
    0.06
    τικά
    0.06
     多
    0.06
     Drama
    0.06
    цеп
    0.06
    lik
    0.06
    antage
    0.06
    Act Density 0.004%

    No Known Activations