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

    Neuronpedia

    INDEX
    Explanations

    making a selection

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ็ก
    -0.07
    αιο
    -0.06
    폴
    -0.06
    -metal
    -0.06
     psychotic
    -0.06
     Listening
    -0.06
     thuật
    -0.06
    Centre
    -0.06
    Development
    -0.06
    _noise
    -0.06
    POSITIVE LOGITS
    告
    0.07
    compiler
    0.07
    .jackson
    0.06
     lider
    0.06
     hurd
    0.06
     Charset
    0.06
    编号
    0.06
    767
    0.06
     гла
    0.06
     mij
    0.06
    Act Density 0.108%

    No Known Activations