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

    Neuronpedia

    INDEX
    Explanations

    drug

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ("{\"
    -0.07
     parm
    -0.06
     Meredith
    -0.06
    �
    -0.06
     Tiles
    -0.06
    LayoutPanel
    -0.06
    +"/
    -0.06
     نظام
    -0.06
     عش
    -0.06
    ):
↵
↵
    -0.06
    POSITIVE LOGITS
    _aug
    0.07
    ASY
    0.07
     clues
    0.06
    Segments
    0.06
    reply
    0.06
    _train
    0.06
     cue
    0.06
    tg
    0.06
     shoots
    0.06
    _CREATE
    0.06
    Act Density 0.000%

    No Known Activations