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

    Neuronpedia

    INDEX
    Explanations

    artificial intelligence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     papp
    0.41
    释
    0.40
     fint
    0.38
     cast
    0.38
     madison
    0.38
     parr
    0.37
    釋
    0.36
     চিত
    0.36
     skewed
    0.36
    rossover
    0.35
    POSITIVE LOGITS
    Coh
    0.46
    Don
    0.44
    Investigation
    0.43
    Emb
    0.43
    When
    0.42
    Artifact
    0.42
    Dur
    0.41
    Frag
    0.41
    Duration
    0.41
    Meeting
    0.41
    Act Density 0.009%

    No Known Activations