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

    Neuronpedia

    INDEX
    Explanations

    positive feelings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     अर
    -0.07
    arguments
    -0.07
    ultural
    -0.07
     seeks
    -0.07
    ATO
    -0.06
     Carpenter
    -0.06
    Driver
    -0.06
     Scandinavian
    -0.06
     Reverse
    -0.06
    quarter
    -0.06
    POSITIVE LOGITS
     mus
    0.06
    _refl
    0.06
     stoi
    0.06
     وكانت
    0.06
    Slow
    0.06
     funkc
    0.06
     BEEN
    0.06
    eax
    0.06
     phổ
    0.06
     jiného
    0.06
    Act Density 0.166%

    No Known Activations