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

    Neuronpedia

    INDEX
    Explanations

    try to fix or do something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    analysis
    0.54
    again
    0.49
    および
    0.48
    및
    0.48
    history
    0.47
    checking
    0.47
    along
    0.46
     अफेयर
    0.46
    guy
    0.46
    and
    0.46
    POSITIVE LOGITS
     terlihat
    0.45
     receptacle
    0.42
     jeruk
    0.42
     Puja
    0.42
     verfü
    0.40
     spont
    0.40
     drin
    0.40
     receptacles
    0.40
     integrante
    0.39
     Zulu
    0.38
    Act Density 0.005%

    No Known Activations