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

    Neuronpedia

    INDEX
    Explanations

    "strings"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     alter
    -0.07
     ACCOUNT
    -0.07
     nrows
    -0.06
     dyst
    -0.06
     meziná
    -0.06
     Gallagher
    -0.06
    .invalidate
    -0.06
     Believe
    -0.06
     Nab
    -0.06
    Forest
    -0.06
    POSITIVE LOGITS
    ALLEL
    0.08
     titre
    0.07
    อากาศ
    0.07
    ANK
    0.07
    ingu
    0.06
    _mE
    0.06
     Iranians
    0.06
     imkân
    0.06
    SEE
    0.06
     BFS
    0.06
    Act Density 0.005%

    No Known Activations