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

    Neuronpedia

    INDEX
    Explanations

    elements related to model trains and tracks

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

    toys, hobbies, models

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     algorithm
    -0.41
     Ume
    -0.41
     Schrift
    -0.41
     JpaRepository
    -0.41
     Winaray
    -0.40
    
    -0.39
    FACE
    -0.39
    stdafx
    -0.39
    Pessoa
    -0.39
     abu
    -0.38
    POSITIVE LOGITS
    ніципалі
    0.52
    encodeWith
    0.52
     Toys
    0.51
     Hobbies
    0.49
    InputBorder
    0.47
     toys
    0.46
     PicClick
    0.43
    玩具
    0.43
    toys
    0.43
    Giới
    0.42
    Act Density 0.003%

    No Known Activations