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

    Neuronpedia

    INDEX
    Explanations

    attracting attention/style

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     uçuş
    -0.08
    esimal
    -0.07
    اوية
    -0.07
     vendor
    -0.07
    lops
    -0.07
     altitude
    -0.06
    ↵	
↵
    -0.06
     unprecedented
    -0.06
    holder
    -0.06
    水平
    -0.06
    POSITIVE LOGITS
    𝘽
    0.08
    _TIM
    0.07
    ᵌ
    0.07
    Grab
    0.07
    ('.'
    0.07
    Ӡ
    0.07
     generosity
    0.07
    作为一个
    0.07
    Ⱄ
    0.07
    ','',
    0.07
    Act Density 0.053%

    No Known Activations