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

    Neuronpedia

    INDEX
    Explanations

    into

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    جر
    -0.07
    	end
    -0.06
    bubble
    -0.06
     blond
    -0.06
     obt
    -0.06
    ARB
    -0.06
     nécess
    -0.06
     oc
    -0.06
    由
    -0.06
    ########################################################
    -0.06
    POSITIVE LOGITS
     Fiat
    0.07
     Casino
    0.07
     LATIN
    0.07
     shops
    0.06
     ресур
    0.06
    พอ
    0.06
     hepatitis
    0.06
    --;
    0.06
     gamb
    0.06
     služ
    0.06
    Act Density 0.084%

    No Known Activations