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

    Neuronpedia

    INDEX
    Explanations

    "you know what" phrase

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (ins
    -0.07
    рел
    -0.07
     tj
    -0.07
     BaseService
    -0.07
     relentless
    -0.06
    ９
    -0.06
     Und
    -0.06
    ULD
    -0.06
    $/
    -0.06
    …
    -0.06
    POSITIVE LOGITS
    امي
    0.07
    _MODAL
    0.06
    _simulation
    0.06
    etically
    0.06
     Comb
    0.06
     plugin
    0.06
     revelation
    0.06
     republic
    0.06
    \Event
    0.06
     đẹp
    0.06
    Act Density 0.082%

    No Known Activations