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

    Neuronpedia

    INDEX
    Explanations

    physical and chemical properties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    /\
    0.44
     genu
    0.43
     connus
    0.42
     estimés
    0.40
     curvil
    0.39
    FLICT
    0.39
     કે
    0.39
     Napier
    0.39
     lahir
    0.38
     circuits
    0.38
    POSITIVE LOGITS
    Selon
    0.49
    ア
    0.48
    tions
    0.47
    बह
    0.45
     Ontology
    0.44
    </a>
    0.44
    rieren
    0.43
    只
    0.43
     לח
    0.42
    一种
    0.41
    Act Density 0.001%

    No Known Activations