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

    Neuronpedia

    INDEX
    Explanations

    receive

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ernes
    -0.08
    (numero
    -0.07
     FN
    -0.07
    Fade
    -0.07
    [*
    -0.07
     fd
    -0.07
    Blockly
    -0.07
    /alert
    -0.06
     btn
    -0.06
    	de
    -0.06
    POSITIVE LOGITS
     consumers
    0.07
    매
    0.07
    寰
    0.07
    RESS
    0.06
    脔
    0.06
    ária
    0.06
    pieces
    0.06
    ISE
    0.06
     réalis
    0.06
    باقي
    0.06
    Act Density 0.051%

    No Known Activations