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
     후
    -0.08
     (++
    -0.07
    จะได
    -0.07
    rám
    -0.07
     improvements
    -0.06
    902
    -0.06
     statue
    -0.06
    .cc
    -0.06
     hs
    -0.06
    ,next
    -0.06
    POSITIVE LOGITS
     contempt
    0.06
    creens
    0.06
    trees
    0.06
     destabil
    0.06
    _but
    0.06
    ーバ
    0.06
    irling
    0.05
    程
    0.05
    Leod
    0.05
    菲
    0.05
    Act Density 0.000%

    No Known Activations