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

    Neuronpedia

    INDEX
    Explanations

    Scientific papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     piping
    -0.07
    返
    -0.06
     "{}
    -0.06
    ِب
    -0.06
    してる
    -0.06
     Loads
    -0.06
    ्रम
    -0.06
     nội
    -0.06
    _VO
    -0.06
    萨
    -0.06
    POSITIVE LOGITS
     underway
    0.07
    Mexico
    0.07
     sufferers
    0.07
     unanimously
    0.07
    (group
    0.06
    átor
    0.06
    redi
    0.06
     laughed
    0.06
     Educ
    0.06
     smoothly
    0.06
    Act Density 0.000%

    No Known Activations