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

    Neuronpedia

    INDEX
    Explanations

    back

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Que
    -0.07
     Pero
    -0.07
     mesure
    -0.07
    Fetcher
    -0.07
     fi
    -0.07
     Decision
    -0.07
    　　 　 　
    -0.06
     jour
    -0.06
    yme
    -0.06
    -source
    -0.06
    POSITIVE LOGITS
     backs
    0.09
     back
    0.08
    ily
    0.06
    TB
    0.06
    Back
    0.06
    _IF
    0.06
     Back
    0.06
    В
    0.06
    ..\
    0.06
     bleach
    0.06
    Act Density 0.009%

    No Known Activations