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

    Neuronpedia

    INDEX
    Explanations

    Concentration and intensity

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .vis
    -0.07
    Ot
    -0.07
    tings
    -0.07
     ur
    -0.07
    ᴩ
    -0.06
    加之
    -0.06
    ologies
    -0.06
    joined
    -0.06
     tucked
    -0.06
    +)/
    -0.06
    POSITIVE LOGITS
    Anti
    0.09
     UIFont
    0.08
    师父
    0.07
    .%
    0.07
    נית
    0.07
    决心
    0.07
     обязатель
    0.07
    チーム
    0.07
     channelId
    0.07
    _UNIFORM
    0.06
    Act Density 0.070%

    No Known Activations