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

    Neuronpedia

    INDEX
    Explanations

    lists and enumerations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     boca
    0.40
     Tycho
    0.40
    傕
    0.40
     Rowling
    0.39
     buttery
    0.39
    乃
    0.39
    𝘞
    0.39
    ἷ
    0.39
     installations
    0.38
     suono
    0.38
    POSITIVE LOGITS
    ardu
    0.41
    Shannon
    0.40
    anatom
    0.39
     Shannon
    0.39
     ११
    0.38
     antit
    0.37
    igil
    0.37
    cream
    0.37
    glad
    0.36
    acrylamide
    0.36
    Act Density 0.003%

    No Known Activations