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

    Neuronpedia

    INDEX
    Explanations

    technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Serena
    -0.07
    erva
    -0.06
    Funny
    -0.06
    �
    -0.06
     бог
    -0.06
    ôi
    -0.06
    .scale
    -0.06
    uckets
    -0.06
    -metal
    -0.06
    807
    -0.06
    POSITIVE LOGITS
    イヤ
    0.08
    vature
    0.07
    Guard
    0.07
     postseason
    0.06
    ,W
    0.06
    CW
    0.06
    >P
    0.06
     muscle
    0.06
     ήταν
    0.06
    �
    0.06
    Act Density 0.000%

    No Known Activations