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

    Neuronpedia

    INDEX
    Explanations

    LAN, debunk, horizons, Gross-Up

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    eba
    0.42
    樁
    0.42
     neve
    0.38
    და
    0.36
    primitive
    0.36
    ினா
    0.36
    ைகிறது
    0.36
    椿
    0.36
     nieve
    0.36
     primitive
    0.36
    POSITIVE LOGITS
     Rout
    0.39
    ږ
    0.38
     sostanz
    0.38
    setIcon
    0.38
     $('<
    0.36
     館
    0.36
     stand
    0.36
     عال
    0.36
    RAP
    0.36
     Policies
    0.36
    Act Density 0.000%

    No Known Activations