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

    Neuronpedia

    INDEX
    Explanations

    Ak

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Han
    -0.06
    Cha
    -0.06
    iado
    -0.06
     Nate
    -0.06
     Yo
    -0.06
    ynos
    -0.06
    _override
    -0.06
    Yang
    -0.06
    		    ↵
    -0.06
     Tob
    -0.06
    POSITIVE LOGITS
    -term
    0.07
    kom
    0.07
     term
    0.07
     окруж
    0.07
     setEmail
    0.07
     vak
    0.06
     Київ
    0.06
     Amit
    0.06
     Automatically
    0.06
    訳
    0.06
    Act Density 0.010%

    No Known Activations