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

    Neuronpedia

    INDEX
    Explanations

    sections, folders, formulas, contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    呕
    0.52
     islets
    0.50
    峎
    0.50
    ापुर
    0.49
    т
    0.49
    őt
    0.48
     islands
    0.47
    敒
    0.47
    䄪
    0.47
    ногда
    0.46
    POSITIVE LOGITS
     belle
    0.46
     STYLE
    0.45
    ati
    0.43
    8
    0.42
    SON
    0.41
     marchio
    0.41
     )
    0.40
     CABINET
    0.39
     सेक्शन
    0.38
     स्टाइल
    0.38
    Act Density 0.001%

    No Known Activations