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

    Neuronpedia

    INDEX
    Explanations

    instances of words containing the substring "fi" or variations thereof

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

    fi, fl, cial, ability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     TestBed
    -0.44
     autorytatywna
    -0.41
    KURZBESCHREIBUNG
    -0.40
    sstil
    -0.39
     Ubicación
    -0.39
    Ǻ
    -0.39
    actéristique
    -0.39
    DockStyle
    -0.38
    henswürdigkeiten
    -0.38
     préférence
    -0.38
    POSITIVE LOGITS
    fi
    1.02
     fi
    0.91
    fl
    0.71
     first
    0.64
     fl
    0.60
    astify
    0.55
    はじめに
    0.51
    ffi
    0.51
     nahilalakip
    0.49
    0.48
    Act Density 0.199%

    No Known Activations