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

    Neuronpedia

    INDEX
    Explanations

    Programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ideally
    -0.07
    いい
    -0.06
    tutorial
    -0.06
    료
    -0.06
    ург
    -0.06
    スペ
    -0.06
     stere
    -0.06
    산업
    -0.06
    tmpl
    -0.06
    fait
    -0.06
    POSITIVE LOGITS
    ForResult
    0.07
     Dont
    0.07
     Wade
    0.06
     توانید
    0.06
    곳
    0.06
     kut
    0.06
    σεις
    0.06
     tooth
    0.06
    边
    0.06
    _scenario
    0.06
    Act Density 0.010%

    No Known Activations