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

    Neuronpedia

    INDEX
    Explanations

    actions and thoughts within a plan

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    transformers
    0.42
    AnimationFrame
    0.40
    modifiers
    0.39
    NetAmount
    0.38
    FhirExtension
    0.37
    Modifiers
    0.37
    lubridate
    0.36
    克力
    0.36
    ▐
    0.36
    MaxScaler
    0.35
    POSITIVE LOGITS
     THINK
    0.54
     Gedanken
    0.52
     thought
    0.50
     мысли
    0.48
     Thought
    0.47
     Think
    0.46
     thoughts
    0.44
     thinks
    0.43
     सोचते
    0.43
     think
    0.42
    Act Density 0.029%

    No Known Activations