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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names associated with political figures and parties

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

    Ali, Yogi, Nunes, Eve

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    sp
    -0.32
     Dich
    -0.30
     she
    -0.30
     Powers
    -0.29
    <'
    -0.29
     Sp
    -0.28
    Portály
    -0.28
     folk
    -0.28
    Rptr
    -0.27
     sp
    -0.26
    POSITIVE LOGITS
    +#+#
    0.72
    ⤹
    0.72
     dieſer
    0.65
     defaultstate
    0.63
     ſeinen
    0.63
     desmotivaciones
    0.63
    httphttps
    0.62
     zijne
    0.62
    VersionUID
    0.61
     dieſen
    0.60
    Act Density 0.005%

    No Known Activations