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

    Neuronpedia

    INDEX
    Explanations

    Repetition and continuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hayal
    -0.07
     yak
    -0.06
     cozy
    -0.06
    Improved
    -0.06
    �
    -0.06
     λα
    -0.06
     saves
    -0.06
     mathematical
    -0.06
    Grade
    -0.06
    hide
    -0.06
    POSITIVE LOGITS
     створ
    0.08
     正
    0.06
    .primary
    0.06
    ταν
    0.06
    .pageSize
    0.06
    _EDGE
    0.06
     Nom
    0.06
    larda
    0.06
     Clinical
    0.06
    ",
↵
    0.06
    Act Density 0.171%

    No Known Activations