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

    Neuronpedia

    INDEX
    Explanations

    quality

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    니스
    -0.07
     Timeout
    -0.07
    italic
    -0.07
    어진
    -0.06
     postage
    -0.06
    hed
    -0.06
    oystick
    -0.06
    avior
    -0.06
    Jonathan
    -0.06
    sterdam
    -0.06
    POSITIVE LOGITS
     природ
    0.07
    .date
    0.06
     mee
    0.06
    _eval
    0.06
    .when
    0.06
     Nacional
    0.06
     TXT
    0.06
    Once
    0.06
     rot
    0.06
    �
    0.06
    Act Density 0.012%

    No Known Activations