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

    Neuronpedia

    INDEX
    Explanations

    credentials

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bio
    -0.09
     био
    -0.09
    bio
    -0.08
    Bio
    -0.08
     fech
    -0.08
     biometric
    -0.08
     Bio
    -0.08
    .bio
    -0.08
     ordenar
    -0.07
     эксперт
    -0.07
    POSITIVE LOGITS
     imperfect
    0.09
     contempt
    0.08
     stolen
    0.08
     stealing
    0.08
     Chen
    0.08
     dysfunctional
    0.08
     underm
    0.08
     steal
    0.08
     poisoning
    0.08
     acquired
    0.08
    Act Density 0.005%

    No Known Activations