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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    351
    -0.07
     might
    -0.07
     costume
    -0.06
    สำ
    -0.06
    ๆ
    -0.06
    plugin
    -0.06
     خواهد
    -0.06
     йому
    -0.06
     ๆ
    -0.06
     terre
    -0.06
    POSITIVE LOGITS
    ),'
    0.07
    +",
    0.07
     contato
    0.06
    _tF
    0.06
     Wrath
    0.06
     Somehow
    0.06
    ùa
    0.06
     getLocation
    0.06
     NavLink
    0.06
     latent
    0.06
    Act Density 0.009%

    No Known Activations