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

    Neuronpedia

    INDEX
    Explanations

    programming questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sowie
    -0.09
    to
    -0.07
     announces
    -0.07
    ();++
    -0.07
     tack
    -0.06
    tür
    -0.06
    Metro
    -0.06
    {})↵
    -0.06
    ,self
    -0.06
     tell
    -0.06
    POSITIVE LOGITS
    娣
    0.07
    _LOW
    0.07
     censorship
    0.07
     Scientists
    0.07
    院士
    0.07
    戗
    0.07
     '?'
    0.06
    Credential
    0.06
    /core
    0.06
    格會
    0.06
    Act Density 0.042%

    No Known Activations