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

    Neuronpedia

    INDEX
    Explanations

    instances of method calls that initialize or retrieve shared instances in code

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

    singleton instance retrieval

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    __':
    -0.65
     فريبيس
    -0.65
     betweenstory
    -0.64
    TypedDataSet
    -0.63
     виправивши
    -0.60
    KommentareTeilen
    -0.57
    Rüyada
    -0.57
    __":
    -0.57
    +#+#
    -0.57
     ModelRenderer
    -0.55
    POSITIVE LOGITS
    getInstance
    0.84
    instance
    0.51
     getInstance
    0.50
    GetInstance
    0.49
    Instance
    0.42
    INSTANCE
    0.42
     instance
    0.40
    vangen
    0.39
     actuels
    0.39
     powerful
    0.39
    Act Density 0.001%

    No Known Activations