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

    Neuronpedia

    INDEX
    Explanations

    terms related to moral and ethical concepts

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

    abstract concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    principalColumn
    -0.63
    IntoConstraints
    -0.56
    addCriterion
    -0.54
     AssemblyCulture
    -0.54
    Хьажоргаш
    -0.52
    Personensuche
    -0.51
     gynhyrchwyd
    -0.50
    ftagPool
    -0.49
     GenerationType
    -0.49
    SequentialGroup
    -0.48
    POSITIVE LOGITS
    Predecesor
    0.37
    strator
    0.36
    zter
    0.36
    häng
    0.35
     pegs
    0.35
    Ligações
    0.35
    brk
    0.34
     незавершена
    0.32
     Zorg
    0.32
    e
    0.32
    Act Density 0.111%

    No Known Activations