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

    Neuronpedia

    INDEX
    Explanations

    repairs and modifications

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    eln
    -0.06
     favorites
    -0.06
    .Control
    -0.06
    iversal
    -0.06
     TS
    -0.06
    _traits
    -0.06
    рин
    -0.06
    Works
    -0.06
     wealth
    -0.06
    휴
    -0.06
    POSITIVE LOGITS
    .↵↵↵↵↵↵
    0.08
    。↵↵↵↵↵↵
    0.07
    Has
    0.06
    饮
    0.06
     συμβ
    0.06
    -has
    0.06
     getPassword
    0.06
    .=
    0.06
     sightings
    0.06
    цький
    0.06
    Act Density 0.133%

    No Known Activations