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

    Neuronpedia

    INDEX
    Explanations

    elements related to user interface components and their interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    code statements ending in punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ſind
    -0.96
     dieſer
    -0.85
    ſchaft
    -0.84
    majánló
    -0.82
    mpagne
    -0.81
     dieſe
    -0.80
     increí
    -0.80
     müſſen
    -0.79
    iſchen
    -0.79
    <unused3>
    -0.79
    POSITIVE LOGITS
    0.31
    MessageTagHelper
    0.29
    ↵↵↵↵↵
    0.28
     mo
    0.28
    ↵↵↵↵
    0.28
     beserta
    0.26
     дописавши
    0.25
    org
    0.24
     umo
    0.24
    Rs
    0.23
    Act Density 0.005%

    No Known Activations