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

    Neuronpedia

    INDEX
    Explanations

    describing unsuccessful attempts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    當
    -0.07
    多少
    -0.06
     ekonomik
    -0.06
     بیشتر
    -0.06
    とい
    -0.06
    PosX
    -0.06
    �
    -0.06
     دانشگاه
    -0.06
    _requested
    -0.06
    巡
    -0.06
    POSITIVE LOGITS
    .nb
    0.07
    aged
    0.07
     Stub
    0.07
     node
    0.07
     น
    0.06
     Unt
    0.06
    where
    0.06
     Elias
    0.06
     Puppet
    0.06
    luv
    0.06
    Act Density 0.117%

    No Known Activations