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

    Neuronpedia

    INDEX
    Explanations

    Doctor

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    脂
    -0.09
     Sz
    -0.08
    .Assign
    -0.08
     predetermined
    -0.08
    �
    -0.08
     Members
    -0.08
    雅
    -0.08
     hundred
    -0.07
     Mitglieder
    -0.07
     POP
    -0.07
    POSITIVE LOGITS
     compassion
    0.09
     Unicorn
    0.09
     Incredible
    0.08
     मुख
    0.08
     экскур
    0.08
     miracles
    0.08
    Tagged
    0.08
    Episode
    0.08
    Episodes
    0.08
     Compassion
    0.08
    Act Density 0.003%

    No Known Activations