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

    Neuronpedia

    INDEX
    Explanations

    code parameters and values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    endez
    0.52
    también
    0.50
     or
    0.50
    IZ
    0.48
    endous
    0.48
    être
    0.46
    table
    0.46
    aremos
    0.46
    rounded
    0.46
    tagged
    0.46
    POSITIVE LOGITS
     the
    0.66
     a
    0.63
     Ei
    0.52
     Afri
    0.52
     Mt
    0.52
     blanditiis
    0.51
     EMP
    0.51
     Aries
    0.51
     AOL
    0.50
     Eg
    0.50
    Act Density 0.166%

    No Known Activations