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

    Neuronpedia

    INDEX
    Explanations

    approximation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     olsun
    -0.10
     varten
    -0.08
     tarv
    -0.08
     gent
    -0.08
     behöver
    -0.08
    heets
    -0.08
    awesome
    -0.08
    marine
    -0.08
    umb
    -0.08
    needs
    -0.07
    POSITIVE LOGITS
     roughly
    0.10
    وفق
    0.09
     according
    0.09
     generally
    0.09
     undocumented
    0.09
     Chrome
    0.08
     generalmente
    0.08
     assez
    0.08
     approximately
    0.08
     Generally
    0.08
    Act Density 0.008%

    No Known Activations