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

    Neuronpedia

    INDEX
    Explanations

    <x

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     recv
    -0.07
    $I
    -0.07
     آباد
    -0.07
     Recipes
    -0.06
     Parents
    -0.06
    urgence
    -0.06
    bill
    -0.06
     greed
    -0.06
    	col
    -0.06
     Seit
    -0.06
    POSITIVE LOGITS
     gated
    0.07
    rollable
    0.06
    utsche
    0.06
    (run
    0.06
    enant
    0.06
    (Packet
    0.06
     almış
    0.06
     HMS
    0.06
    出了
    0.06
    (DEBUG
    0.06
    Act Density 0.004%

    No Known Activations