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

    Neuronpedia

    INDEX
    Explanations

    code involving lengths/indices

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _DEFIN
    -0.07
     thinking
    -0.06
     جد
    -0.06
    �
    -0.06
     upholstery
    -0.06
     ReturnType
    -0.06
     besoin
    -0.06
     Ost
    -0.06
    inizin
    -0.06
     backed
    -0.06
    POSITIVE LOGITS
     quar
    0.07
    도
    0.06
    opathic
    0.06
    +'&
    0.06
     Incoming
    0.06
     dhcp
    0.06
     vigorously
    0.06
    -initialized
    0.06
    ibaba
    0.06
     addition
    0.06
    Act Density 0.098%

    No Known Activations