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

    Neuronpedia

    INDEX
    Explanations

    -ity or -ness

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Bytes
    0.40
    мир
    0.38
    ᔨ
    0.37
    )--(
    0.37
    ].[
    0.37
     teniendo
    0.36
    ipasi
    0.36
     Jeb
    0.35
     Shreve
    0.35
     Hodge
    0.35
    POSITIVE LOGITS
     Iceland
    0.37
    ability
    0.36
     accountability
    0.36
    мін
    0.36
    ué
    0.36
     freshness
    0.35
    ality
    0.34
     creativity
    0.33
    ítő
    0.33
    VL
    0.33
    Act Density 0.002%

    No Known Activations