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

    Neuronpedia

    INDEX
    Explanations

    laws of physics and philosophy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fertiliser
    0.39
     concetto
    0.38
    aksikan
    0.37
     provisions
    0.37
    岩
    0.37
     개념
    0.36
     mewah
    0.36
     promete
    0.35
     moelle
    0.35
     پژوه
    0.35
    POSITIVE LOGITS
     thermodynamics
    0.52
     probability
    0.50
     Thermodynamics
    0.49
     locality
    0.49
     superposition
    0.47
     reciprocity
    0.47
     probabilities
    0.47
     Probability
    0.46
     logarithms
    0.46
     solubility
    0.46
    Act Density 0.013%

    No Known Activations