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

    Neuronpedia

    INDEX
    Explanations

    have

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     отримання
    -0.07
    .Ship
    -0.07
     Пр
    -0.06
     thụ
    -0.06
    �
    -0.06
     Cr
    -0.06
    eacher
    -0.06
     sponsored
    -0.06
    xcc
    -0.06
    (Util
    -0.06
    POSITIVE LOGITS
    weights
    0.08
     telescope
    0.07
    (itemView
    0.06
    BIND
    0.06
     turbulence
    0.06
    ','
    0.06
     ~/.
    0.06
     irq
    0.06
    elihood
    0.06
    _room
    0.06
    Act Density 0.001%

    No Known Activations