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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	This
    -0.06
    Team
    -0.06
    20
    -0.06
    _optional
    -0.06
     Nir
    -0.06
     về
    -0.06
     وال
    -0.06
    .names
    -0.06
    ###↵
    -0.05
    matches
    -0.05
    POSITIVE LOGITS
     abst
    0.07
    경제
    0.07
    iyi
    0.07
    χν
    0.06
    .preventDefault
    0.06
     pizza
    0.06
     Voyager
    0.06
     Tur
    0.06
    ardon
    0.06
    ửi
    0.06
    Act Density 0.013%

    No Known Activations