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

    Neuronpedia

    INDEX
    Explanations

    11

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	control
    -0.06
    (hand
    -0.06
    Strip
    -0.06
    SP
    -0.06
    ISTS
    -0.06
    _STR
    -0.06
    INGER
    -0.06
    ERA
    -0.05
    YRO
    -0.05
    hů
    -0.05
    POSITIVE LOGITS
    思想
    0.07
     #'
    0.07
     Saskatchewan
    0.07
     Freeze
    0.07
    outil
    0.07
     vời
    0.07
    기간
    0.06
    Machine
    0.06
     Newton
    0.06
     patched
    0.06
    Act Density 0.016%

    No Known Activations