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

    Neuronpedia

    INDEX
    Explanations

    directory paths, dirname

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Беларусь
    0.54
    ownic
    0.49
    ,*/}
    0.47
    ነስ
    0.47
    <unused199>
    0.46
    <unused990>
    0.46
    Belarus
    0.46
    successor
    0.45
     белару
    0.45
    تين
    0.44
    POSITIVE LOGITS
    0.68
     a
    0.50
    2
    0.50
     monomer
    0.49
     due
    0.48
     values
    0.48
     response
    0.47
     Route
    0.47
     Rockstar
    0.47
     pt
    0.46
    Act Density 0.009%

    No Known Activations