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

    Neuronpedia

    INDEX
    Explanations

    regret

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .ByteString
    -0.07
    青年
    -0.06
     isEmpty
    -0.06
    hcp
    -0.06
    ollower
    -0.06
    =admin
    -0.06
    ()),
    -0.06
    cons
    -0.06
     değildir
    -0.06
     bs
    -0.06
    POSITIVE LOGITS
     конт
    0.06
     losses
    0.06
    -saving
    0.06
     rotating
    0.06
    COME
    0.06
    Compile
    0.06
    ản
    0.06
    _again
    0.06
    abl
    0.06
     작업
    0.06
    Act Density 0.010%

    No Known Activations