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

    Neuronpedia

    INDEX
    Explanations

    edit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (title
    -0.07
    -eyed
    -0.06
     vmax
    -0.06
    StringBuilder
    -0.06
     Rey
    -0.06
     Bilim
    -0.06
     rej
    -0.06
     Increase
    -0.06
    _HT
    -0.06
    _RA
    -0.06
    POSITIVE LOGITS
    ανά
    0.07
     scripted
    0.07
     Before
    0.07
     penny
    0.06
    .*;
↵
    0.06
     мені
    0.06
     PS
    0.06
     keen
    0.06
     undesirable
    0.06
    ADDE
    0.06
    Act Density 0.015%

    No Known Activations