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

    Neuronpedia

    INDEX
    Explanations

    reference counting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     soit
    -0.08
     tern
    -0.07
    ANTA
    -0.07
    sense
    -0.07
    りと
    -0.07
     vacant
    -0.06
     getaway
    -0.06
    -drive
    -0.06
    회
    -0.06
    .dashboard
    -0.06
    POSITIVE LOGITS
    ",$
    0.06
    _family
    0.06
    ült
    0.06
    .changed
    0.06
     dereg
    0.06
    当然
    0.06
     toolkit
    0.06
     reprint
    0.06
    ANCED
    0.06
     ülke
    0.06
    Act Density 0.006%

    No Known Activations