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

    Neuronpedia

    INDEX
    Explanations

    generating images or text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gebied
    0.50
    úz
    0.49
     fáb
    0.47
     campo
    0.46
     giảm
    0.46
    án
    0.44
     magicians
    0.44
    MORDOR
    0.43
    ších
    0.43
     mView
    0.43
    POSITIVE LOGITS
    ре
    0.60
    J
    0.52
    Y
    0.51
    ی
    0.50
    Х
    0.49
    У
    0.49
    ори
    0.48
    З
    0.48
    Action
    0.46
    ?
    0.46
    Act Density 0.001%

    No Known Activations