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

    Neuronpedia

    INDEX
    Explanations

    support

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    grid
    -0.07
     hodin
    -0.07
    ením
    -0.06
     juice
    -0.06
    _grid
    -0.06
    IVE
    -0.06
    ícul
    -0.06
     imagination
    -0.06
     Time
    -0.06
     OSI
    -0.06
    POSITIVE LOGITS
     엄
    0.07
     Conserv
    0.07
    П
    0.07
     sulph
    0.06
    port
    0.06
     믿
    0.06
    (separator
    0.06
     용
    0.06
    وات
    0.06
    pet
    0.06
    Act Density 0.006%

    No Known Activations