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

    Neuronpedia

    INDEX
    Explanations

    renewable

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -0.07
    opal
    -0.07
    !!
    -0.06
    imit
    -0.06
     inhibitor
    -0.06
    -0.06
     bổ
    -0.06
     찬
    -0.06
    	X
    -0.06
    Lu
    -0.06
    POSITIVE LOGITS
    (rand
    0.07
     getText
    0.07
    aspberry
    0.06
     meslek
    0.06
     fourn
    0.06
     Người
    0.06
     hours
    0.06
     xml
    0.06
     gruesome
    0.06
    atatype
    0.06
    Act Density 0.011%

    No Known Activations