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

    Neuronpedia

    INDEX
    Explanations

    negative feelings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Oakland
    -0.07
    .extern
    -0.07
     instructions
    -0.07
    _week
    -0.07
     inference
    -0.06
     PBS
    -0.06
    otics
    -0.06
    Es
    -0.06
     Kraft
    -0.06
     pessim
    -0.06
    POSITIVE LOGITS
     έχ
    0.07
     ดร
    0.06
     trailing
    0.06
    '];?>
    0.06
     initializing
    0.06
    ząd
    0.06
    >(↵
    0.06
     Majority
    0.06
     необходимо
    0.06
    ’ye
    0.06
    Act Density 0.059%

    No Known Activations