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

    Neuronpedia

    INDEX
    Explanations

    2017 paper

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    currently
    1.12
    av
    0.97
     currently
    0.93
    目前
    0.92
    author
    0.92
     today
    0.90
    2
    0.89
    mess
    0.88
    fr
    0.87
    today
    0.87
    POSITIVE LOGITS
     edition
    1.20
     সালের
    1.12
    ′
    1.10
     iteration
    1.06
    版的
    1.02
    পন্থী
    1.01
     Spinach
    1.01
    版本的
    1.00
     dwRes
    0.99
     deluge
    0.99
    Act Density 0.015%

    No Known Activations