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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    好
    -0.07
    니까
    -0.07
    toHave
    -0.07
    .keywords
    -0.07
     Rings
    -0.06
    /new
    -0.06
     или
    -0.06
     好
    -0.06
    Stub
    -0.06
     jerk
    -0.06
    POSITIVE LOGITS
    uns
    0.07
     Concern
    0.06
    Alias
    0.06
    ucle
    0.06
     ACPI
    0.06
    	JOptionPane
    0.06
    .Action
    0.06
    .en
    0.06
    -validation
    0.06
    tera
    0.06
    Act Density 0.020%

    No Known Activations