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

    Neuronpedia

    INDEX
    Explanations

    code and file names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    نين
    -0.07
    ۱۴
    -0.07
     influence
    -0.06
    FIXME
    -0.06
     Tango
    -0.06
    ขาย
    -0.06
     件
    -0.06
     цьому
    -0.06
    39
    -0.06
    794
    -0.06
    POSITIVE LOGITS
     вз
    0.07
     Venez
    0.07
    licate
    0.07
    ADX
    0.06
    ebilir
    0.06
    αιδ
    0.06
    	CHECK
    0.06
     vẻ
    0.06
    ılması
    0.06
     mne
    0.06
    Act Density 0.000%

    No Known Activations