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

    Neuronpedia

    INDEX
    Explanations

    private conversations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Unix
    -0.07
     Charge
    -0.06
    :bold
    -0.06
     Pierre
    -0.06
     Drake
    -0.06
     CHP
    -0.06
     getResult
    -0.06
     HL
    -0.06
    ,pos
    -0.06
    Consider
    -0.06
    POSITIVE LOGITS
    ежду
    0.07
    nofollow
    0.06
     sodom
    0.06
     συμμε
    0.06
    γκα
    0.06
    .array
    0.06
    537
    0.06
    ату
    0.06
     Jackets
    0.06
    odář
    0.06
    Act Density 0.058%

    No Known Activations