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

    Neuronpedia

    INDEX
    Explanations

    Common grammatical tokens

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     +'
    -0.07
    -health
    -0.07
     Lig
    -0.06
     stare
    -0.06
     Cristina
    -0.06
     }};↵
    -0.06
    agal
    -0.06
    Into
    -0.06
     blinded
    -0.06
    -negative
    -0.06
    POSITIVE LOGITS
     desert
    0.07
    ском
    0.06
    naments
    0.06
    .w
    0.06
    <>↵
    0.06
    ogram
    0.06
    _tools
    0.06
    anlar
    0.06
     질문
    0.06
    _beam
    0.06
    Act Density 0.028%

    No Known Activations