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

    Neuronpedia

    INDEX
    Explanations

    phrases related to component interactions and configurations

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

    parts or components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     univerz
    -0.24
     pocz
    -0.23
     lanz
    -0.23
    gnąć
    -0.22
    섰
    -0.22
    amazonaws
    -0.21
    дца
    -0.21
     immune
    -0.20
     pair
    -0.20
     traffic
    -0.20
    POSITIVE LOGITS
     parts
    1.38
     Parts
    1.27
    parts
    1.27
    Parts
    1.23
     PARTS
    1.20
     part
    1.10
    PARTS
    1.09
    part
    1.05
     partes
    1.02
     Teile
    1.02
    Act Density 0.179%

    No Known Activations