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

    Neuronpedia

    INDEX
    Explanations

    is, are, can

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     encounters
    0.51
     sanity
    0.49
     therefore
    0.47
     panic
    0.46
     instances
    0.44
     encounter
    0.43
     aware
    0.42
     parents
    0.42
     profit
    0.42
     quale
    0.42
    POSITIVE LOGITS
    б
    0.55
    вана
    0.54
    أ
    0.53
    ចេ
    0.52
     Rubio
    0.52
     válv
    0.51
    с
    0.50
    ".[
    0.50
     поможет
    0.49
    algorithms
    0.49
    Act Density 0.203%

    No Known Activations