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

    Neuronpedia

    INDEX
    Explanations

    outlines/borders

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (storage
    -0.07
    13
    -0.06
    さんの
    -0.06
     bốn
    -0.06
     France
    -0.06
     ruin
    -0.06
     wing
    -0.06
    .richTextBox
    -0.06
    Incorrect
    -0.06
     århus
    -0.06
    POSITIVE LOGITS
    rens
    0.07
    GN
    0.06
    ційного
    0.06
    TXT
    0.06
     عد
    0.06
    licants
    0.06
     मतलब
    0.06
     SETTINGS
    0.06
    upil
    0.06
    _FORCE
    0.06
    Act Density 0.017%

    No Known Activations