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

    Neuronpedia

    INDEX
    Explanations

    message

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .’”↵↵
    -0.07
    amu
    -0.07
    ㊟
    -0.07
    asp
    -0.07
    缕
    -0.07
    win
    -0.06
    .setStyle
    -0.06
     skip
    -0.06
    涌
    -0.06
    どの
    -0.06
    POSITIVE LOGITS
    是韩国
    0.08
    (express
    0.07
     Paragraph
    0.07
    (ff
    0.07
    _singular
    0.07
     iliş
    0.07
    直言
    0.07
    Leg
    0.07
    .feedback
    0.07
    .setCharacter
    0.07
    Act Density 0.001%

    No Known Activations