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

    Neuronpedia

    INDEX
    Explanations

    tree * Australia

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Lah
    0.78
     Pleasant
    0.75
     Arche
    0.75
     Mitigation
    0.73
     Conservancy
    0.71
     Formation
    0.70
     Theft
    0.70
     Residence
    0.70
     Interpretation
    0.70
     Predator
    0.70
    POSITIVE LOGITS
    omnia
    0.93
    identical
    0.78
    Под
    0.78
    ară
    0.76
    exclude
    0.76
     कीमत
    0.76
    공
    0.75
    послед
    0.73
    த்தே
    0.73
    打算
    0.73
    Act Density 0.000%

    No Known Activations