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

    Neuronpedia

    INDEX
    Explanations

    {

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Waters
    -0.08
    .cwd
    -0.07
    summary
    -0.07
     دار
    -0.07
     amplified
    -0.07
     вод
    -0.07
    ังไม
    -0.06
    опри
    -0.06
     квар
    -0.06
    ifications
    -0.06
    POSITIVE LOGITS
    效果
    0.06
     Identify
    0.06
    険
    0.06
    abei
    0.06
    vably
    0.06
     หน
    0.06
     ByteArray
    0.06
    átor
    0.06
     girişim
    0.06
    震
    0.06
    Act Density 0.001%

    No Known Activations