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

    Neuronpedia

    INDEX
    Explanations

    diagrams, plots, graphs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    assi
    -0.06
     防
    -0.06
     functionalities
    -0.06
    řiv
    -0.06
    undi
    -0.06
    _own
    -0.06
    239
    -0.06
     داش
    -0.06
    Negative
    -0.06
    जह
    -0.06
    POSITIVE LOGITS
    !!)↵
    0.07
     SENT
    0.07
     ach
    0.07
     cod
    0.07
    iciency
    0.06
    asured
    0.06
    logan
    0.06
    ByteArray
    0.06
    gon
    0.06
     Pittsburgh
    0.06
    Act Density 0.130%

    No Known Activations