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

    Neuronpedia

    INDEX
    Explanations

    code comments

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     //
    3.07
    //
    2.57
     #
    2.21
     //-
    1.91
     //<
    1.84
     ///
    1.84
     //!
    1.82
    ,//
    1.81
     ////
    1.78
     /*
    1.77
    POSITIVE LOGITS
     בן
    0.71
     proponents
    0.68
    पृ
    0.68
    కూ
    0.67
     precedents
    0.65
     programmatic
    0.65
    ᅩ
    0.64
     arrondissement
    0.64
     üzere
    0.64
     unabhängig
    0.64
    Act Density 0.255%

    No Known Activations