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

    Neuronpedia

    INDEX
    Explanations

    fence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     wonderful
    0.42
     lottery
    0.42
     ceremony
    0.38
     nationally
    0.37
     proceedings
    0.37
     charter
    0.36
     suces
    0.36
     Latvian
    0.36
     amazing
    0.36
     spectacular
    0.35
    POSITIVE LOGITS
    Neigh
    0.35
     disebabkan
    0.32
    ೇಕ
    0.31
    åll
    0.31
    音が
    0.30
    原因是
    0.30
    तें
    0.30
     zákon
    0.30
     Zweck
    0.30
    ḥ
    0.29
    Act Density 0.001%

    No Known Activations