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

    Neuronpedia

    INDEX
    Explanations

    Reinforcement schedules in animal experiments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     GIF
    -0.07
     seaside
    -0.07
     WriteLine
    -0.07
    WiFi
    -0.06
     اخت
    -0.06
     Germans
    -0.06
     attrib
    -0.06
     ΕΠ
    -0.06
    ディース
    -0.06
    robat
    -0.06
    POSITIVE LOGITS
     ==============================================================
    0.07
     consideration
    0.07
    allery
    0.07
    ancer
    0.07
    .modified
    0.06
     τους
    0.06
     ngược
    0.06
     Nombre
    0.06
    �
    0.06
     цел
    0.06
    Act Density 0.015%

    No Known Activations