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

    Neuronpedia

    INDEX
    Explanations

    technical terms and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ل
    0.59
    lardan
    0.56
    те
    0.56
    larda
    0.56
    ers
    0.55
    lng
    0.54
    l
    0.54
    lara
    0.53
    eritud
    0.53
    lty
    0.52
    POSITIVE LOGITS
    U
    0.54
     it
    0.52
     la
    0.51
     can
    0.48
     so
    0.46
     amazingly
    0.46
     be
    0.45
    ется
    0.44
     awe
    0.44
     go
    0.44
    Act Density 0.478%

    No Known Activations