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

    Neuronpedia

    INDEX
    Explanations

    numbers and expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    elfs
    -0.95
     following
    -0.90
    tersebut
    -0.83
    arson
    -0.81
    président
    -0.80
    руется
    -0.79
     Gouver
    -0.77
     siguientes
    -0.77
    Revel
    -0.77
     mépris
    -0.77
    POSITIVE LOGITS
     so
    0.86
    thirty
    0.85
     each
    0.84
     Fourteen
    0.83
     niečo
    0.80
    twelve
    0.80
     từng
    0.79
    ErrUnexpectedEOF
    0.79
     Gar
    0.78
     Nineteen
    0.78
    Act Density 0.155%

    No Known Activations