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

    Neuronpedia

    INDEX
    Explanations

    names of specific individuals or characters

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

    given names followed by surnames

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tlv
    -0.44
    ardless
    -0.43
     Pullman
    -0.43
    DockStyle
    -0.42
    limus
    -0.40
     DiCaprio
    -0.40
    Schritt
    -0.40
    ticus
    -0.39
     Sephora
    -0.39
    ContextHolder
    -0.38
    POSITIVE LOGITS
     wikipagina
    0.51
    GEBURTSDATUM
    0.49
     AssemblyProduct
    0.45
     ComVisible
    0.43
     nød
    0.41
     jugé
    0.40
     isNameExpr
    0.40
    ://$
    0.40
    Rhestr
    0.39
     mať
    0.39
    Act Density 0.093%

    No Known Activations