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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating existence or presence

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

    "There is" or "There are" phrases

    np_acts-logits-general · gemini-2.0-flash

    there is and there are constructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Vors
    -0.65
    ();)
    -0.65
    ModelSerializer
    -0.59
     estekak
    -0.53
     Inſ
    -0.53
     "..\..\..\
    -0.52
    }*/
    -0.52
    Unmarshaller
    -0.51
     çap
    -0.50
    hamma
    -0.50
    POSITIVE LOGITS
     truly
    0.65
    truly
    0.57
    󠁿
    0.56
    HostException
    0.55
    nonatomic
    0.55
     Truly
    0.55
    
    0.54
    RenderAtEndOf
    0.54
    cerer
    0.53
    COUVER
    0.51
    Act Density 0.084%

    No Known Activations