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

    Neuronpedia

    INDEX
    Explanations

    deep

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -N
    -0.07
    06
    -0.07
    -Life
    -0.07
     Tips
    -0.07
    Mark
    -0.07
     rating
    -0.07
    Plus
    -0.07
     Ellen
    -0.06
    -life
    -0.06
    ился
    -0.06
    POSITIVE LOGITS
     Praze
    0.06
    0.06
     farther
    0.06
    ㅎ
    0.06
    kelig
    0.06
     GroupLayout
    0.06
    partment
    0.06
    (COLOR
    0.06
    <lemma
    0.06
    (Unknown
    0.06
    Act Density 0.011%

    No Known Activations