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

    Neuronpedia

    INDEX
    Explanations

    mathematical derivations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    094
    -0.09
     eiusmod
    -0.09
    Cold
    -0.08
    dialog
    -0.08
     moni
    -0.08
    Pas
    -0.08
     pas
    -0.08
    Episode
    -0.08
     épisodes
    -0.08
    Episodes
    -0.08
    POSITIVE LOGITS
     derived
    0.10
     చేసిన
    0.10
    -derived
    0.10
     Derived
    0.09
     inadvertently
    0.08
    derived
    0.08
     जिसने
    0.08
     необ
    0.08
    했던
    0.08
     valid
    0.08
    Act Density 0.034%

    No Known Activations