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

    Neuronpedia

    INDEX
    Explanations

    skills

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     listopadu
    -0.07
     ponder
    -0.07
     alınan
    -0.07
    onden
    -0.06
     Dialogue
    -0.06
     August
    -0.06
    oodoo
    -0.06
    Post
    -0.06
     rozhodnutí
    -0.06
     آمده
    -0.06
    POSITIVE LOGITS
     skills
    0.20
     Skills
    0.15
     skill
    0.12
    skills
    0.10
    .skills
    0.10
     Skill
    0.10
    skill
    0.10
    _skill
    0.09
    Skills
    0.09
    Skill
    0.09
    Act Density 0.020%

    No Known Activations