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

    Neuronpedia

    INDEX
    Explanations

    People

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (hit
    -0.06
     sentence
    -0.06
     disruptive
    -0.06
     kann
    -0.06
    ưa
    -0.06
    Responder
    -0.06
    fixed
    -0.06
    .fetchall
    -0.06
    ooting
    -0.06
     enthusiast
    -0.06
    POSITIVE LOGITS
     Mol
    0.07
     Cor
    0.07
    .mu
    0.07
    .sulake
    0.07
     offic
    0.07
     esl
    0.06
     мы
    0.06
     writers
    0.06
    snippet
    0.06
    ۵
    0.06
    Act Density 0.057%

    No Known Activations