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

    Neuronpedia

    INDEX
    Explanations

    has

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    譬如
    -0.07
     Thickness
    -0.07
    inct
    -0.07
     Freud
    -0.06
    aded
    -0.06
     HIM
    -0.06
    るので
    -0.06
    由
    -0.06
    正確
    -0.06
    Used
    -0.06
    POSITIVE LOGITS
    ㅑ
    0.07
     redistributed
    0.07
    走廊
    0.07
     iid
    0.07
     tồ
    0.07
     goto
    0.06
    自救
    0.06
    ("`
    0.06
     rose
    0.06
    โน
    0.06
    Act Density 0.136%

    No Known Activations