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

    Neuronpedia

    INDEX
    Explanations

    tell

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     arrangement
    -0.07
    ��
    -0.06
     abuse
    -0.06
     Makeup
    -0.06
     cómo
    -0.06
     zvol
    -0.06
    archs
    -0.06
    ünd
    -0.06
    Funny
    -0.06
    _lower
    -0.06
    POSITIVE LOGITS
     physicists
    0.08
     √
    0.06
    亞
    0.06
    overflow
    0.06
    _BLK
    0.06
    亚
    0.06
     THEORY
    0.06
    -u
    0.06
     gunshot
    0.06
     shelf
    0.06
    Act Density 0.017%

    No Known Activations