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

    Neuronpedia

    INDEX
    Explanations

    history sections

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     вопрос
    -0.06
    iště
    -0.06
     Х
    -0.06
    Sky
    -0.06
     Niagara
    -0.06
     kendi
    -0.06
    사무
    -0.06
     Tort
    -0.06
     вы
    -0.06
    <X
    -0.06
    POSITIVE LOGITS
     Jag
    0.07
     america
    0.06
     mankind
    0.06
     Characters
    0.06
    -paying
    0.06
    цией
    0.06
     Phill
    0.06
    refer
    0.06
     risen
    0.06
     addicted
    0.06
    Act Density 0.025%

    No Known Activations