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

    Neuronpedia

    INDEX
    Explanations

    names of geographical features

    oai_token-act-pair · gemini-2.0-flash

    mountains and regions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    coroutines
    -0.63
     مرئيه
    -0.53
    +#+#
    -0.47
    iprot
    -0.44
    ByEmail
    -0.42
    ichord
    -0.41
    ficit
    -0.41
    permitAll
    -0.41
    pores
    -0.40
     deserialize
    -0.39
    POSITIVE LOGITS
     mountain
    1.17
     mountains
    1.14
     Mountain
    1.09
    mountains
    1.03
     Mountains
    1.03
    Mountain
    1.02
     MOUNTAIN
    0.98
    mountain
    0.95
     montagne
    0.93
     mountaine
    0.93
    Act Density 0.362%

    No Known Activations