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

    Neuronpedia

    INDEX
    Explanations

    specific categories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Примеча
    0.43
     याबाबत
    0.39
    am
    0.37
     formulaire
    0.36
    什么是
    0.36
    સ
    0.36
    용
    0.36
    дел
    0.35
    তিক
    0.35
    retien
    0.35
    POSITIVE LOGITS
     qubits
    0.40
     domains
    0.39
     ratings
    0.39
    :,
    0.38
     risiko
    0.37
     phonons
    0.37
     ions
    0.36
     lubricants
    0.36
     causal
    0.36
     bior
    0.36
    Act Density 0.168%

    No Known Activations