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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "from."

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

    from moc, from user, <start_of_turn> user

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     devrez
    -0.19
     أح
    -0.19
     pos
    -0.18
    appartamento
    -0.18
     repos
    -0.17
     chêne
    -0.17
    แจ
    -0.17
     keber
    -0.17
    träger
    -0.17
     deberá
    -0.16
    POSITIVE LOGITS
    存于互联网档案馆
    1.02
     ujednoznacz
    0.91
     Administrativna
    0.89
    UserScript
    0.88
     disambiguazione
    0.85
     <<<<<<<<<<<<<<
    0.84
    0.83
    oa̍t
    0.82
    esModule
    0.82
    __(/*!
    0.81
    Act Density 0.000%

    No Known Activations