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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     знов
    -0.06
    �
    -0.06
    昌
    -0.06
     historia
    -0.06
    _HIDE
    -0.06
    KD
    -0.06
    eny
    -0.06
    pragma
    -0.05
    ･･
    -0.05
     dny
    -0.05
    POSITIVE LOGITS
     trainer
    0.07
    来说
    0.06
    λέ
    0.06
     Ear
    0.06
    ..↵
    0.06
     dead
    0.06
     граждан
    0.06
    ιστή
    0.06
    슴
    0.06
    .↵
    0.06
    Act Density 0.000%

    No Known Activations