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

    Neuronpedia

    INDEX
    Explanations

    scientific concepts and terminology related to physics

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

    crossover, convergence, dependence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     administ
    -0.36
    administ
    -0.35
     Instant
    -0.35
     hag
    -0.34
    urk
    -0.32
    instant
    -0.32
     ADMINISTR
    -0.32
    ADMINISTR
    -0.32
    Administ
    -0.31
     Probab
    -0.31
    POSITIVE LOGITS
     dependence
    1.01
     dependency
    0.85
     dependencia
    0.82
    dependence
    0.79
     dependencies
    0.79
     Dependence
    0.77
     Dependencies
    0.69
    dependency
    0.69
     Dependency
    0.68
     dépend
    0.68
    Act Density 0.309%

    No Known Activations