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

    Neuronpedia

    INDEX
    Explanations

    per

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _activate
    -0.07
    /todo
    -0.07
     ItemType
    -0.06
     focuses
    -0.06
    suma
    -0.06
    Translatef
    -0.06
    mux
    -0.06
    l
    -0.06
     Transmit
    -0.06
    bz
    -0.06
    POSITIVE LOGITS
     advanced
    0.07
     接
    0.07
     ACE
    0.07
     proportional
    0.06
    Illuminate
    0.06
    하지
    0.06
     experi
    0.06
    ings
    0.06
     therapeutic
    0.06
     clinically
    0.06
    Act Density 0.003%

    No Known Activations