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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     IEntity
    -0.07
    /down
    -0.07
    (var
    -0.07
     MainWindow
    -0.06
     UIManager
    -0.06
    μαι
    -0.06
     Alaska
    -0.06
     kaf
    -0.06
    uty
    -0.06
     jot
    -0.06
    POSITIVE LOGITS
    ΥΡ
    0.07
     formulations
    0.06
     harms
    0.06
     The
    0.06
    τος
    0.06
     Geological
    0.06
     преступ
    0.06
     consultation
    0.06
    致
    0.06
     "'"
    0.06
    Act Density 0.036%

    No Known Activations