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

    Neuronpedia

    INDEX
    Explanations

    programming syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     乾燥
    0.25
     oxidación
    0.25
    Raquete
    0.24
    ncnc
    0.24
     व्हाउचर
    0.23
     couvre
    0.23
     oxidize
    0.22
     المثلثيه
    0.22
    <unused344>
    0.22
    bottlecap
    0.22
    POSITIVE LOGITS
    import
    0.34
    void
    0.29
    t
    0.28
    my
    0.28
    class
    0.27
    public
    0.27
    java
    0.26
    const
    0.25
    try
    0.25
    d
    0.25
    Act Density 0.275%

    No Known Activations