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

    Neuronpedia

    INDEX
    Explanations

    screenplay/script

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    辦
    -0.06
    “As
    -0.06
    implemented
    -0.06
    “No
    -0.06
     BR
    -0.06
     박
    -0.06
     knows
    -0.06
    "B
    -0.06
     lest
    -0.06
     McK
    -0.06
    POSITIVE LOGITS
     informant
    0.07
    keh
    0.07
    .visualization
    0.07
    ‰
    0.07
    |:
    0.06
    いつ
    0.06
    .activation
    0.06
    ={},
    0.06
    _detach
    0.06
     FFT
    0.06
    Act Density 0.006%

    No Known Activations