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

    Neuronpedia

    INDEX
    Explanations

    golden descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Bukh
    0.59
     Dever
    0.47
     Staub
    0.46
     gambler
    0.45
     Bucs
    0.43
     CNBC
    0.43
     Bree
    0.43
     Desen
    0.43
     Mastery
    0.43
    +'-
    0.42
    POSITIVE LOGITS
    Prince
    0.49
    T
    0.46
    Ad
    0.45
    Province
    0.45
    Robert
    0.45
    Ses
    0.45
    OrEqualTo
    0.44
    C
    0.44
    E
    0.44
    Tin
    0.43
    Act Density 0.001%

    No Known Activations