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

    Neuronpedia

    INDEX
    Explanations

    product descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     obedient
    -0.07
     terrifying
    -0.06
     mez
    -0.06
    :flutter
    -0.06
    -card
    -0.06
     fian
    -0.06
    igmoid
    -0.06
     دام
    -0.06
     looks
    -0.06
    .encrypt
    -0.06
    POSITIVE LOGITS
    _sin
    0.07
    emode
    0.07
     fundraiser
    0.07
    _STENCIL
    0.07
    işi
    0.06
     بازیگر
    0.06
    _bus
    0.06
     retorna
    0.06
     نویس
    0.06
    _SINGLE
    0.06
    Act Density 0.061%

    No Known Activations