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

    Neuronpedia

    INDEX
    Explanations

    attack

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .drawLine
    -0.07
    _ser
    -0.07
    (NO
    -0.07
    _SCHED
    -0.06
     أكتوبر
    -0.06
    百
    -0.06
    modelo
    -0.06
    см
    -0.06
     کر
    -0.06
    	param
    -0.06
    POSITIVE LOGITS
     Chips
    0.06
     dicts
    0.06
    Latch
    0.06
     Mich
    0.06
     Specifically
    0.06
     Levi
    0.06
    ToAdd
    0.06
    /The
    0.06
     preorder
    0.06
     ASS
    0.06
    Act Density 0.020%

    No Known Activations