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

    Neuronpedia

    INDEX
    Explanations

    Ter

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Beam
    -0.07
     ")
    -0.07
     paradigm
    -0.06
    indered
    -0.06
     Joi
    -0.06
    ีฟ
    -0.06
     Payne
    -0.06
    _employee
    -0.06
     beams
    -0.06
     Ctrl
    -0.06
    POSITIVE LOGITS
     Family
    0.08
    inality
    0.07
    ิตภ
    0.07
    :white
    0.07
     테
    0.07
     secret
    0.06
     Ter
    0.06
    /sm
    0.06
    (completion
    0.06
    .Local
    0.06
    Act Density 0.012%

    No Known Activations