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

    Neuronpedia

    INDEX
    Explanations

    Eastern

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     supportive
    -0.07
     :'
    -0.06
     hypothetical
    -0.06
     delete
    -0.06
    Always
    -0.06
    047
    -0.06
    plates
    -0.06
     fancy
    -0.06
     producto
    -0.06
    .Temp
    -0.06
    POSITIVE LOGITS
    .ExecuteScalar
    0.06
     Erotische
    0.06
    mad
    0.06
     Faculty
    0.06
     پل
    0.06
    _
↵
↵
    0.06
    adoo
    0.06
     Аф
    0.06
    SingleOrDefault
    0.06
    -scalable
    0.06
    Act Density 0.002%

    No Known Activations