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

    Neuronpedia

    INDEX
    Explanations

    wondering how or about

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    declar
    0.44
     yours
    0.42
     vulcan
    0.42
     funz
    0.42
    DECL
    0.41
    decl
    0.41
    िफ्ट
    0.41
    Ammo
    0.40
    vu
    0.40
    हूं
    0.40
    POSITIVE LOGITS
     Propri
    0.45
     Sharing
    0.40
     ప్రేక్ష
    0.38
     তিক্ত
    0.38
    行業
    0.38
     Scalars
    0.37
    哪些
    0.37
     потом
    0.37
    ('>
    0.36
     Practitioner
    0.36
    Act Density 0.002%

    No Known Activations