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

    Neuronpedia

    INDEX
    Explanations

    various excerpts

    np_max-act · gemini-2.0-flash

    dialogue and interactions that emphasize playful and teasing communication in personal relationships.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     astronomy
    -0.07
     Sunrise
    -0.06
     emphasizing
    -0.06
    lm
    -0.06
    -show
    -0.06
     practise
    -0.06
    926
    -0.05
    พวกเข
    -0.05
    сут
    -0.05
     organism
    -0.05
    POSITIVE LOGITS
     tunnels
    0.07
     Stores
    0.07
    .getResult
    0.07
     actualizar
    0.06
    Di
    0.06
     sensit
    0.06
     Nero
    0.06
    Comparable
    0.06
    -trans
    0.06
    Interpreter
    0.06
    Act Density 0.046%

    No Known Activations