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

    Neuronpedia

    INDEX
    Explanations

    safe

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    contri
    -0.07
     책
    -0.07
    	height
    -0.07
    //--
    -0.06
     받아
    -0.06
     кноп
    -0.06
     subscriptions
    -0.06
    _help
    -0.06
    นาย
    -0.06
    iet
    -0.06
    POSITIVE LOGITS
    steady
    0.06
     Blockly
    0.06
    (org
    0.06
     pll
    0.06
     믿
    0.06
    zzle
    0.06
    นวย
    0.06
     vivastreet
    0.06
    TLS
    0.06
    руп
    0.06
    Act Density 0.005%

    No Known Activations