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

    Neuronpedia

    INDEX
    Explanations

    Code and technical documentation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ㇺ
    -0.07
     sıcak
    -0.07
     Câm
    -0.07
     dissatisfaction
    -0.07
     הבוקר
    -0.07
    客气
    -0.07
     bruises
    -0.07
     cellphone
    -0.07
     immunity
    -0.07
    -hours
    -0.07
    POSITIVE LOGITS
     between
    0.08
    	catch
    0.07
    anton
    0.07
     leading
    0.07
    ž
    0.07
     advise
    0.07
     including
    0.07
    出土
    0.07
    ]))↵↵
    0.07
     event
    0.07
    Act Density 0.000%

    No Known Activations