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

    Neuronpedia

    INDEX
    Explanations

    citation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Tag
    -0.08
    cesso
    -0.07
    ác
    -0.07
    リアル
    -0.07
    олж
    -0.07
    люч
    -0.07
     Accum
    -0.07
    disc
    -0.07
    �
    -0.07
    �
    -0.07
    POSITIVE LOGITS
     SW
    0.07
    ![↵
    0.07
     CW
    0.07
     (#
    0.06
     Physician
    0.06
    增强了
    0.06
     היטב
    0.06
    .Sm
    0.06
     bicycles
    0.06
    大批
    0.06
    Act Density 0.000%

    No Known Activations