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

    Neuronpedia

    INDEX
    Explanations

    string values, especially names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     such
    -1.59
     universite
    -1.53
     staden
    -1.39
     egen
    -1.32
     zoals
    -1.31
    мец
    -1.30
     the
    -1.30
    -1.30
     Pada
    -1.29
     Universiteit
    -1.29
    POSITIVE LOGITS
     about
    1.59
     trov
    1.52
    籟
    1.46
    岀
    1.45
    ⦊
    1.44
    ৄ
    1.37
     Apparently
    1.36
     who
    1.32
     Entdecken
    1.30
     żad
    1.30
    Act Density 0.144%

    No Known Activations