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

    Neuronpedia

    INDEX
    Explanations

    Documents with formal dates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     STATUS
    -0.07
    afone
    -0.07
    Communic
    -0.07
    _contin
    -0.06
    岂
    -0.06
     gü
    -0.06
    -season
    -0.06
    *np
    -0.06
    _tweets
    -0.06
    (account
    -0.06
    POSITIVE LOGITS
    要把
    0.07
     Auckland
    0.07
    las
    0.07
    /";↵↵
    0.07
    졵
    0.06
    滧
    0.06
    	Intent
    0.06
     Eva
    0.06
    '");↵
    0.06
    Popup
    0.06
    Act Density 0.048%

    No Known Activations