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

    Neuronpedia

    INDEX
    Explanations

    months

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _connection
    -0.08
     Leather
    -0.07
    -(
    -0.07
     Monte
    -0.07
    ircular
    -0.07
    λου
    -0.07
    aments
    -0.06
    requencies
    -0.06
    (`
    -0.06
    Inventory
    -0.06
    POSITIVE LOGITS
     např
    0.07
     обяз
    0.07
    .package
    0.06
     škola
    0.06
    ламент
    0.06
     reperc
    0.06
     passphrase
    0.06
     �
    0.06
    ']])↵
    0.06
     sach
    0.06
    Act Density 0.021%

    No Known Activations