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

    Neuronpedia

    INDEX
    Explanations

    moon to earth

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kiddos
    0.56
     idyllic
    0.52
    ารณา
    0.50
    ds
    0.50
     ibid
    0.50
     class
    0.49
     undergrad
    0.49
     linf
    0.49
     id
    0.48
    )}{
    0.47
    POSITIVE LOGITS
    Pol
    0.47
    Will
    0.46
    Cast
    0.46
    Schedule
    0.46
    Tek
    0.46
    Broker
    0.45
    棰
    0.45
    Pressure
    0.45
    Ré
    0.44
    Tec
    0.43
    Act Density 0.001%

    No Known Activations