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

    Neuronpedia

    INDEX
    Explanations

    less

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    kra
    -0.08
    úsica
    -0.08
    wechsl
    -0.08
    interrupt
    -0.08
     sociaux
    -0.08
     disagree
    -0.08
    igações
    -0.08
     Israël
    -0.08
     кто
    -0.08
    pruch
    -0.07
    POSITIVE LOGITS
    ാതെ
    0.10
    ாமல்
    0.09
    ుండా
    0.08
    ാത്ത
    0.08
     없이
    0.07
     tanpa
    0.07
     ini
    0.07
     approaches
    0.07
     Magdal
    0.07
    -ақ
    0.07
    Act Density 0.028%

    No Known Activations