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

    Neuronpedia

    INDEX
    Explanations

    place names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vaisse
    0.23
    <unused2162>
    0.22
    <unused2152>
    0.21
     ahuv
    0.21
    <unused2168>
    0.21
     ROUILLER
    0.20
    𒁾
    0.20
    綀
    0.20
    <unused2155>
    0.20
    mataspid
    0.20
    POSITIVE LOGITS
     St
    0.31
     K
    0.31
     Port
    0.30
     San
    0.29
     S
    0.29
     Fort
    0.29
     Lake
    0.28
     O
    0.28
     T
    0.28
     P
    0.28
    Act Density 0.051%

    No Known Activations