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

    Neuronpedia

    INDEX
    Explanations

    programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     "()
    -0.07
     Whats
    -0.07
    =None
    -0.07
    帝国
    -0.07
    .wx
    -0.06
     whats
    -0.06
    _hp
    -0.06
     شر
    -0.06
     ICollection
    -0.06
    SMS
    -0.06
    POSITIVE LOGITS
     Hercules
    0.07
     homicide
    0.06
     complained
    0.06
    elled
    0.05
     Dylan
    0.05
    OUTH
    0.05
    騎
    0.05
    elah
    0.05
    仪
    0.05
     Trường
    0.05
    Act Density 0.017%

    No Known Activations