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

    Neuronpedia

    INDEX
    Explanations

    ="

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ¢
    -0.07
    ве
    -0.06
    Entries
    -0.06
     boasting
    -0.06
     clase
    -0.06
    swana
    -0.06
     слов
    -0.06
     dentist
    -0.06
     stereo
    -0.06
     restau
    -0.06
    POSITIVE LOGITS
    :]↵↵
    0.07
    });↵↵↵
    0.06
    免
    0.06
     persecuted
    0.06
     Trib
    0.06
    (auth
    0.06
    ]])↵↵
    0.06
     setValue
    0.06
    lys
    0.06
     frm
    0.06
    Act Density 0.002%

    No Known Activations