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

    Neuronpedia

    INDEX
    Explanations

    concepts related to unity and collaboration among groups

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

    unify, unite, united, union

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.66
    "}";
    -0.63
     незавершена
    -0.59
    ########.
    -0.58
     HasFactory
    -0.56
    }();
    -0.54
     sno
    -0.52
    iastical
    -0.52
     fres
    -0.51
     Starling
    -0.51
    POSITIVE LOGITS
     cohesion
    0.76
     unido
    0.73
     compacto
    0.67
     lazos
    0.67
     Divided
    0.67
     uniting
    0.66
     cohesive
    0.65
     unified
    0.64
     unifying
    0.63
     divisive
    0.63
    Act Density 0.044%

    No Known Activations