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

    Neuronpedia

    INDEX
    Explanations

    named entities and related concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ссив
    0.43
    濬
    0.43
    ArgsEnv
    0.42
     állapot
    0.40
    atoires
    0.39
    ఙ
    0.39
    UserProg
    0.39
    Compression
    0.38
     अवस्थ
    0.38
    軐
    0.38
    POSITIVE LOGITS
     highlighted
    0.61
     highlighting
    0.60
     highlight
    0.58
    highlight
    0.54
     Highlight
    0.53
     выде
    0.51
     destaque
    0.51
     contextual
    0.50
    Highlight
    0.49
     highlighter
    0.49
    Act Density 0.115%

    No Known Activations