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

    Neuronpedia

    INDEX
    Explanations

    Document

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ])):↵
    -0.07
     cannabinoids
    -0.07
     Fitz
    -0.07
     młod
    -0.06
     jus
    -0.06
    .status
    -0.06
     casinos
    -0.06
    InRange
    -0.06
    idak
    -0.06
    𬭯
    -0.06
    POSITIVE LOGITS
    igers
    0.07
    刺
    0.07
    习惯
    0.07
    �能
    0.06
    自制
    0.06
    本事
    0.06
    rollers
    0.06
     ego
    0.06
    ublic
    0.06
     added
    0.06
    Act Density 0.001%

    No Known Activations