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

    Neuronpedia

    INDEX
    Explanations

    the input

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     singular
    1.02
     Brandon
    0.98
     Ariana
    0.96
     scream
    0.96
     Terre
    0.93
    3
    0.93
     undefined
    0.90
     Kant
    0.90
     resell
    0.89
    singular
    0.88
    POSITIVE LOGITS
    ↵↵↵
    1.47
    ↵↵↵↵
    1.39
    .`
    1.18
    ↵↵↵↵↵
    1.18
    .]
    1.13
    ↵↵↵↵↵↵
    1.13
    ↵↵↵↵↵↵↵
    1.13
    !<
    1.08
     synopsis
    1.08
    FEC
    1.08
    Act Density 0.479%

    No Known Activations