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

    Neuronpedia

    INDEX
    Explanations

    Scientific publications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /videos
    -0.07
    .pop
    -0.07
    .Direct
    -0.07
    iệ
    -0.07
    ethe
    -0.06
     Victor
    -0.06
    těl
    -0.06
     sixth
    -0.06
     affidavit
    -0.06
    .Yes
    -0.06
    POSITIVE LOGITS
    홍
    0.07
     ดาว
    0.07
     WOM
    0.06
    getReference
    0.06
     sond
    0.06
    0.06
     shorts
    0.06
    มหาว
    0.06
                    
    0.06
    -D
    0.06
    Act Density 0.135%

    No Known Activations