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

    Neuronpedia

    INDEX
    Explanations

    references to rivers and related geographical features

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

    appearing before "River" or "Creek"

    np_acts-logits-general · gemini-2.0-flash

    rivers and waterways

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ModelRenderer
    -0.58
    études
    -0.57
    CodeAttribute
    -0.54
     vendu
    -0.52
    eapon
    -0.51
     rigide
    -0.49
     compréhension
    -0.49
    +#+
    -0.49
    vän
    -0.49
     vendus
    -0.49
    POSITIVE LOGITS
    SerializedName
    0.71
     basin
    0.65
     river
    0.64
     waters
    0.63
     River
    0.61
     Réponses
    0.59
     waterway
    0.58
     flowing
    0.58
     water
    0.55
     rivers
    0.55
    Act Density 0.202%

    No Known Activations