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

    Neuronpedia

    INDEX
    Explanations

    action and hobbies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     урож
    -0.07
    .band
    -0.07
    .gz
    -0.06
    ERICAN
    -0.06
     MK
    -0.06
     empres
    -0.06
     reint
    -0.06
     Hz
    -0.06
     Scripture
    -0.06
     BL
    -0.06
    POSITIVE LOGITS
     playing
    0.08
     writing
    0.07
     running
    0.07
     Writing
    0.07
    Writing
    0.07
     spending
    0.07
     listening
    0.07
    %;
↵
    0.07
    (Student
    0.07
    stackpath
    0.07
    Act Density 0.070%

    No Known Activations