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

    Neuronpedia

    INDEX
    Explanations

    references to various types of environments

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

    environment; environments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Infórmanos
    -0.52
     noDo
    -0.50
     Inscrivez
    -0.49
     Sosten
    -0.47
     Cientí
    -0.46
     Artículos
    -0.45
    GEBURTSDATUM
    -0.45
    stylers
    -0.44
     Nacionales
    -0.44
     Sociales
    -0.43
    POSITIVE LOGITS
     environments
    1.27
     Environments
    1.20
    environments
    1.09
    Environ
    0.91
     environment
    0.91
     Environ
    0.75
     env
    0.75
     ambientes
    0.75
     prostředí
    0.74
     Environment
    0.73
    Act Density 0.013%

    No Known Activations