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

    Neuronpedia

    INDEX
    Explanations

    Tor

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    렌
    -0.08
    spiel
    -0.07
     Early
    -0.07
    mae
    -0.07
    rible
    -0.07
    �
    -0.07
     acclaim
    -0.06
     Cheap
    -0.06
    番号
    -0.06
    ЎыџN
    -0.06
    POSITIVE LOGITS
     Tor
    0.14
     tor
    0.12
    Thor
    0.12
     Thor
    0.11
    Tor
    0.11
     tors
    0.10
     TOR
    0.10
     thor
    0.10
    or
    0.09
    OR
    0.09
    Act Density 0.005%

    No Known Activations