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

    Neuronpedia

    INDEX
    Explanations

    prime followed by specific terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lowa
    -0.83
     complying
    -0.81
    ↵↵
    -0.77
     mites
    -0.76
    érèse
    -0.76
     amplify
    -0.75
     broaden
    -0.75
     IFR
    -0.75
     mics
    -0.74
     verfügen
    -0.73
    POSITIVE LOGITS
     mover
    1.59
    Prime
    1.52
     factorization
    1.49
     minister
    1.46
     Prime
    1.42
    val
    1.40
    prime
    1.39
     Minister
    1.38
     prime
    1.23
    Minister
    1.23
    Act Density 0.013%

    No Known Activations