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

    Neuronpedia

    INDEX
    Explanations

    money

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Π
    -0.07
     aesthetics
    -0.07
     journalist
    -0.06
    tons
    -0.06
    _packet
    -0.06
     �
    -0.06
     Mou
    -0.06
    �
    -0.06
    _LOCAL
    -0.06
    당
    -0.06
    POSITIVE LOGITS
    izada
    0.06
     goat
    0.06
     Playboy
    0.06
     электри
    0.06
     convertible
    0.06
     Sevent
    0.06
     �
    0.06
    것
    0.06
    -established
    0.06
     Colomb
    0.06
    Act Density 0.020%

    No Known Activations