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

    Neuronpedia

    INDEX
    Explanations

    weight loss

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     PyQt
    -0.07
    .B
    -0.07
    _BOOT
    -0.06
     προ
    -0.06
     Week
    -0.06
     ns
    -0.06
    raig
    -0.06
     cheaper
    -0.06
    _TER
    -0.06
    .Load
    -0.06
    POSITIVE LOGITS
    EEEE
    0.07
    dn
    0.06
    layers
    0.06
     استر
    0.06
     teleport
    0.06
    =$('#
    0.06
    cribes
    0.06
    мот
    0.06
    ектив
    0.06
    panic
    0.06
    Act Density 0.017%

    No Known Activations