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

    Neuronpedia

    INDEX
    Explanations

    references to data types

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

    data types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     söyle
    -0.35
     magasins
    -0.32
    Lateral
    -0.31
    belong
    -0.30
    Bioaccumulative
    -0.30
     sobě
    -0.30
     quedado
    -0.29
     commerces
    -0.29
     incendios
    -0.28
    र्शन
    -0.28
    POSITIVE LOGITS
    Types
    2.34
     Types
    1.84
    TYPES
    1.49
     TYPES
    1.30
    Tipos
    1.22
     Tipos
    1.10
    types
    1.07
    ypes
    1.05
    tipos
    0.94
    Виды
    0.91
    Act Density 0.003%

    No Known Activations