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

    Neuronpedia

    INDEX
    Explanations

    musical complexity and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Integrity
    0.39
     Proper
    0.38
     photoshoot
    0.37
     Públic
    0.37
     Metropolitan
    0.36
     Re
    0.35
     Binding
    0.35
     Achieving
    0.34
     Metropolitana
    0.34
    hxx
    0.34
    POSITIVE LOGITS
    complex
    0.43
    luence
    0.41
    රක
    0.41
    quantidade
    0.40
    heiro
    0.40
     quei
    0.40
     desperation
    0.39
    ogeneities
    0.39
     сложных
    0.39
    \}=
    0.38
    Act Density 0.000%

    No Known Activations