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

    Neuronpedia

    INDEX
    Explanations

    products

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    بدأ
    -0.07
     代
    -0.06
     Updates
    -0.06
    bie
    -0.06
     बनन
    -0.06
     Timeline
    -0.06
    (metrics
    -0.06
     Calling
    -0.06
     Evolution
    -0.06
     glaciers
    -0.06
    POSITIVE LOGITS
    さま
    0.07
    "type
    0.06
    .$
    0.06
     ''),↵
    0.06
    -prom
    0.06
    ="'.$
    0.06
    -step
    0.06
    )set
    0.06
    .radioButton
    0.06
    lara
    0.06
    Act Density 0.016%

    No Known Activations