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

    Neuronpedia

    INDEX
    Explanations

    years and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    垓
    -0.82
    achter
    -0.80
    lexer
    -0.79
    洒落
    -0.79
    🚲
    -0.79
     cubos
    -0.78
     ***!
    -0.78
    🏍
    -0.77
     Junge
    -0.77
    ador
    -0.77
    POSITIVE LOGITS
     Netanyahu
    1.00
     tymp
    0.86
     joe
    0.84
     carbu
    0.83
     PMS
    0.83
     Springsteen
    0.83
     Matcha
    0.82
     spind
    0.81
     spir
    0.79
     Decl
    0.79
    Act Density 0.069%

    No Known Activations