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

    Neuronpedia

    INDEX
    Explanations

    review terms and conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     glide
    0.47
    ູ້
    0.47
     farce
    0.41
     isotherm
    0.39
    ियर्स
    0.39
     nause
    0.39
    upol
    0.39
     omnichannel
    0.38
     hopelessly
    0.38
     safes
    0.38
    POSITIVE LOGITS
     بواسطة
    0.39
    JUL
    0.37
     Penny
    0.37
    <0x80>
    0.36
    the
    0.36
     Using
    0.36
    fromUtf
    0.36
    Penny
    0.36
    Using
    0.36
     Forming
    0.35
    Act Density 0.001%

    No Known Activations