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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a past lack of knowledge

    oai_token-act-pair · gemini-2.0-flash

    words related to perception

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ujednoznacz
    -0.50
    Erreferentziak
    -0.46
    StoryboardSegue
    -0.46
    BufferException
    -0.45
    COMMERCIAL
    -0.44
    makeText
    -0.44
    articulo
    -0.43
    openqa
    -0.43
    -0.43
    ondissement
    -0.42
    POSITIVE LOGITS
     seen
    1.10
     heard
    1.02
     saw
    0.96
    Seen
    0.94
     Seen
    0.90
    seen
    0.88
     SEEN
    0.85
     SAW
    0.82
    Saw
    0.81
    heard
    0.81
    Act Density 1.214%

    No Known Activations