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

    Neuronpedia

    INDEX
    Explanations

    partner and territories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Zoro
    0.57
     Timurtaş
    0.56
    Ash
    0.55
     Та
    0.54
     Administrator
    0.52
     Symfony
    0.51
    Ис
    0.51
    Э
    0.51
     Verlag
    0.50
     Ис
    0.50
    POSITIVE LOGITS
    s
    0.73
    meal
    0.53
     flooring
    0.47
    defined
    0.47
    akit
    0.47
    population
    0.47
    filtered
    0.46
    dimension
    0.46
    tej
    0.46
    u
    0.46
    Act Density 0.000%

    No Known Activations