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

    Neuronpedia

    INDEX
    Explanations

    Music references

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     titled
    -0.07
     free
    -0.07
    (the
    -0.06
     twenties
    -0.06
     Ben
    -0.06
     academic
    -0.06
     направ
    -0.06
    Ben
    -0.06
     sig
    -0.06
     pine
    -0.06
    POSITIVE LOGITS
    .firestore
    0.06
    égor
    0.06
     تعیین
    0.06
    ným
    0.06
    catid
    0.06
     doz
    0.06
     спе
    0.06
    MLS
    0.06
    HTML
    0.06
     Αγ
    0.06
    Act Density 0.014%

    No Known Activations