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

    Neuronpedia

    INDEX
    Explanations

    the phrases "an X to" or "a stop to".

    oai_token-act-pair · gemini-2.0-flash

    endings and attention

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tableFuture
    -0.70
     Référence
    -0.69
    complexType
    -0.63
    twimg
    -0.59
     censiti
    -0.57
     kaarangay
    -0.56
     nonatomic
    -0.53
    COUVER
    -0.52
    TagHelpers
    -0.51
    cisa
    -0.48
    POSITIVE LOGITS
    сылкі
    0.76
    IntoConstraints
    0.63
    bewerken
    0.60
     defaultstate
    0.60
    marken
    0.59
    runApp
    0.58
    SharedCtor
    0.57
    VersionUID
    0.55
    urp
    0.55
    nelse
    0.53
    Act Density 1.669%

    No Known Activations