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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    一双
    -0.07
    Union
    -0.07
     Icelandic
    -0.07
    ╓
    -0.07
    STATE
    -0.07
    ∝
    -0.06
    phis
    -0.06
    /Internal
    -0.06
    Colorado
    -0.06
     Без
    -0.06
    POSITIVE LOGITS
    (QWidget
    0.07
    (properties
    0.07
     Lect
    0.07
    Mind
    0.07
    \<^
    0.07
    _logs
    0.06
    لح
    0.06
    (href
    0.06
    	pw
    0.06
    iameter
    0.06
    Act Density 0.003%

    No Known Activations