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

    Neuronpedia

    INDEX
    Explanations

    mice research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    だ
    -0.07
    セ
    -0.06
    INU
    -0.06
     вмі
    -0.06
    Vue
    -0.06
    �
    -0.06
     guess
    -0.06
    رف
    -0.06
    Tube
    -0.06
    付
    -0.06
    POSITIVE LOGITS
    spent
    0.07
    ист
    0.07
     ICT
    0.06
     edilmiştir
    0.06
     Quentin
    0.06
     agitation
    0.06
    211
    0.06
     Conditioning
    0.06
     поряд
    0.06
    .Butter
    0.06
    Act Density 0.021%

    No Known Activations