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

    Neuronpedia

    INDEX
    Explanations

    Counseling and therapy

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    едь
    -0.07
    ']))↵
    -0.07
    _SCRIPT
    -0.07
    �
    -0.07
    rese
    -0.07
     ",");↵
    -0.06
    "))
↵
    -0.06
     "))↵
    -0.06
    (mysql
    -0.06
    preferences
    -0.06
    POSITIVE LOGITS
     mpl
    0.07
    -Am
    0.07
     dummy
    0.07
     можете
    0.07
     gente
    0.07
    观点
    0.07
     poignant
    0.06
    国庆
    0.06
    建党
    0.06
    أت
    0.06
    Act Density 0.046%

    No Known Activations