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

    Neuronpedia

    INDEX
    Explanations

    introductions and meetings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Incident
    -0.08
     Incident
    -0.07
     Fein
    -0.07
     Extra
    -0.07
    (FILE
    -0.07
     mirë
    -0.07
    .LO
    -0.07
    Source
    -0.07
    Incoming
    -0.07
    _EXTRA
    -0.07
    POSITIVE LOGITS
     각각
    0.23
    分别
    0.22
     jeweils
    0.16
     المختلفة
    0.16
    ，各
    0.15
    各
    0.15
     chacune
    0.15
     unterschiedlichen
    0.15
     الثلاث
    0.14
     afzonder
    0.14
    Act Density 0.210%

    No Known Activations