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

    Neuronpedia

    INDEX
    Explanations

    code comments and declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Acetic
    0.52
    Monter
    0.45
    Brist
    0.44
    C
    0.44
    R
    0.44
    Trimethyl
    0.43
    Monica
    0.43
    Gary
    0.42
    Vals
    0.42
    Hern
    0.42
    POSITIVE LOGITS
     //
    0.70
    ↵
    0.49
    ;//
    0.46
     /*
    0.45
    ↵↵
    0.45
     gebruikt
    0.44
     gebruiken
    0.44
    つまり
    0.43
     用于
    0.40
     यानी
    0.39
    Act Density 0.069%

    No Known Activations