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

    Neuronpedia

    INDEX
    Explanations

    General text/dialogue fragments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .rpm
    -0.06
    soft
    -0.06
    _portal
    -0.06
     witnessing
    -0.06
    Campaign
    -0.06
    heten
    -0.06
     forgot
    -0.06
     disagreement
    -0.06
    _FORE
    -0.06
     �
    -0.06
    POSITIVE LOGITS
    (O
    0.06
    IDE
    0.06
     Approximately
    0.06
    摄
    0.06
     ();
↵
    0.06
     gy
    0.06
    (Image
    0.06
     REP
    0.06
    ).^
    0.06
     quirky
    0.06
    Act Density 0.000%

    No Known Activations