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

    Neuronpedia

    INDEX
    Explanations

    li

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .DataGridViewColumn
    -0.08
     marrying
    -0.07
     undefeated
    -0.07
     سف
    -0.07
     Umb
    -0.06
    loggedIn
    -0.06
     accents
    -0.06
     literals
    -0.06
    |#
    -0.06
    Ş
    -0.06
    POSITIVE LOGITS
    }<
    0.07
     Canonical
    0.07
     responding
    0.07
    wash
    0.07
    بر
    0.06
     Catholics
    0.06
     прежде
    0.06
     春
    0.06
    _GO
    0.06
    尊
    0.06
    Act Density 0.002%

    No Known Activations