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

    Neuronpedia

    INDEX
    Explanations

    instruments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    kol
    -0.07
     subplot
    -0.07
    mlink
    -0.07
    _EXPECT
    -0.06
     çek
    -0.06
     -*-
↵
    -0.06
    _scenario
    -0.06
    wood
    -0.06
     Quang
    -0.06
    　j
    -0.06
    POSITIVE LOGITS
     har
    0.07
    rupt
    0.06
    	Integer
    0.06
     hap
    0.06
    apped
    0.06
    rpm
    0.06
    ाहर
    0.06
    自
    0.06
     позволя
    0.06
    书
    0.06
    Act Density 0.001%

    No Known Activations