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

    Neuronpedia

    INDEX
    Explanations

    Names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Form
    -0.08
     uart
    -0.07
    (lbl
    -0.07
    Operator
    -0.07
     uv
    -0.07
    folder
    -0.07
    -business
    -0.07
    ฟร
    -0.07
     ef
    -0.06
     Confirmation
    -0.06
    POSITIVE LOGITS
    汗
    0.06
    ）は
    0.06
    
    0.06
    produce
    0.06
    inkle
    0.06
     në
    0.06
     Illustrated
    0.06
    �
    0.05
     가입
    0.05
    insky
    0.05
    Act Density 0.002%

    No Known Activations