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

    Neuronpedia

    INDEX
    Explanations

    wage increases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ertia
    -0.07
     Bowling
    -0.06
    sb
    -0.06
    icate
    -0.06
    Row
    -0.06
    USB
    -0.06
     mas
    -0.06
    _OPTION
    -0.05
    /q
    -0.05
     oro
    -0.05
    POSITIVE LOGITS
     committed
    0.07
     &[
    0.07
     downturn
    0.07
    umericUpDown
    0.07
     llama
    0.06
     srdce
    0.06
     converted
    0.06
    _CRITICAL
    0.06
    _slow
    0.06
     purported
    0.06
    Act Density 0.015%

    No Known Activations